{"benchmark":"VLMBench","version":"v1","generated":"2026-06-07T22:19:21+00:00","expected_runs":30,"models":[{"summary":{"model":"claude_opus_4_7","name":"Claude Opus 4.7","total_evals":550,"total_cells":16500,"l2_cells":15098,"l3_cells":1286,"l4_cells":116,"acceptable":99.3,"runs":30,"partial":false,"l2_evals":495,"l3_evals":49,"l4_evals":6},"evals":[{"eval_id":"019dfb17-0cc4-74a1-8d62-afab29ef1e82","probe":"What is the third bulleted item under the list of electronic and internet-based financial solutions?","golden":"cryptocurrency, including stablecoins","png_sha":"704943f48019c6bab8cb509e1ddeb6f9b48085007ac9101976ed3d04798ac274","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities\n"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities\n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities\n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities\n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities\n"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"tokenized securities"}]},{"eval_id":"019e0524-2f26-7e2d-b1d6-9d9e4787d2c7","probe":"How many additional sponsors were added to H.R. 21?","golden":"8","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"7\n"},{"run_index":1,"verdict":4,"source":"human","note":"wrong count","answer":"7\n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"7\n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"7\n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"7\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":6,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":7,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":8,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":9,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":10,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":11,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":12,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":13,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":14,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":15,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":16,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":17,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":18,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":19,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":20,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":21,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":22,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":23,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":24,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":25,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":26,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":27,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":28,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":29,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"}]},{"eval_id":"019dfb22-9390-7dca-91a4-198eb5ec30b4","probe":"What is the amortized cost net of ACL for Baa rated securities as of December 31, 2022?","golden":"$81,280 million","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"81,280\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"81,280\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"81,280\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"81,280\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$81,280 million"}]},{"eval_id":"019e000b-683c-7e54-aaf2-3d634ac03517","probe":"What is the total expenses for Education in Graph MDA-5?","golden":"$46,073 million","png_sha":"3f8e2c78a2134ddb79f740cc731c989a29e5b11d89cdb0254e1f1740d44cfdb0","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"}]},{"eval_id":"019e00ac-faaf-7e38-b571-92ff92b76932","probe":"Garcia of California voted in which column?","golden":"NAYS","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS\n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":7,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":15,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":16,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":17,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":19,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"}]},{"eval_id":"019e0529-025b-7daa-a5e9-a453809b33ba","probe":"How many sponsors were added to H. Res. 23?","golden":"15","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"14\n"},{"run_index":1,"verdict":4,"source":"human","note":"wrong count","answer":"13\n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"13\n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"14\n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"14\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":6,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":7,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":8,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":9,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":10,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":11,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":12,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":13,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":14,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":16,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":17,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":18,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":20,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":21,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":22,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":23,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":25,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":26,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":27,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":28,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":29,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"}]},{"eval_id":"019de200-d4ba-7ebb-acf4-de78451b07c1","probe":"How many miles is mentioned for relocation of the Executive's principal place of employment?","golden":"25 miles","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"25\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"25\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"25\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"25\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"25\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":12,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25)"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":15,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25)"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":17,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25)"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"}]},{"eval_id":"019de200-d4f1-7b08-800d-39648227b1fc","probe":"How many days advance notice must Tenant give for an Acceleration Notice?","golden":"120 days","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"}]},{"eval_id":"019de200-d507-733d-8d8c-87040ba6130c","probe":"How many days does Landlord have to give Tenant a termination notice after submission of the statement?","golden":"30 days","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"30\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"30\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"30\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"30\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"30\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":17,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30)"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"}]},{"eval_id":"019de200-d508-7af1-93e1-8436c404657e","probe":"How many business days in advance must Tenant provide the Notice of Permitted Transfer?","golden":"10 Business Days","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"}]},{"eval_id":"019de200-d50e-7050-b563-d96d07356800","probe":"How many times per day must the exterior of the building be inspected and maintained?","golden":"four times per day","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four"}]},{"eval_id":"019de200-d515-7626-bd30-2e0c3b0c3b7f","probe":"Within how many Business Days must Borrower pay any excess if it results from a reserve against the Borrowing Base?","golden":"five (5) Business Days","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019de200-d523-7d03-9cf0-aa0eb615e454","probe":"Within how many calendar days following lease termination must Lessor conduct and deliver the Phase I environmental assessment under section 11.4?","golden":"fifteen (15) calendar days","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"}]},{"eval_id":"019de200-d525-7710-85f5-fc41b54afbb0","probe":"Within how many calendar days must Lessee deliver a signed counterpart of the sublease agreement to Lessor after its execution?","golden":"five (5) calendar days","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019dfaef-4f26-7d15-9caf-4928cafc4f5e","probe":"What is the exhibit number shown at the top right of this page?","golden":"Exhibit 23.1","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"}]},{"eval_id":"019dfb3f-d06a-7547-a4b6-8a6e4c150c61","probe":"What is the suite number of the office address listed at the bottom of the letter?","golden":"Suite 1850","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"}]},{"eval_id":"019e0005-d4aa-7f1f-8391-f99f6caf3697","probe":"How many City Council Members are from Brooklyn?","golden":"16 Members","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"}]},{"eval_id":"019e0006-0655-7fe4-88c4-d697fbcb759a","probe":"How many Council Members does Queens have?","golden":"14 Members","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"}]},{"eval_id":"019e0081-be2e-71be-9017-964db6e9e08a","probe":"What is the maximum value shown on the map's mile scale bar?","golden":"45 Miles","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"}]},{"eval_id":"019e0085-cd0d-7043-93eb-a33714bb645a","probe":"What GASB Statement number did the Council adopt in fiscal year 2024?","golden":"No. 96","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"}]},{"eval_id":"019e00a4-d8d8-7d76-84d9-c255fd95f7cd","probe":"How many minutes is Mrs. Trahan recognized for?","golden":"5 minutes","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019e00ad-aa7b-733c-8e2b-33b7f30d7cfc","probe":"Did Senator Whittaker appear on this vote?","golden":"No, Whittaker is not listed on this page","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":6,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":7,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":8,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":9,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":10,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":11,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":12,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":13,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":14,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":15,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":16,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":17,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":18,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":19,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":20,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":21,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":22,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":23,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":24,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":25,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":26,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":27,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":28,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":29,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"}]},{"eval_id":"019e00af-5886-7c0c-acb0-3467635835d6","probe":"What time did the recorded vote take place (the \u25a1 time stamp before the McGOVERN demand)?","golden":"1:56 PM (1356)","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"}]},{"eval_id":"019e00af-a493-76fe-9fc1-0e6baa42ab53","probe":"What time did the House return from recess (the \u25a1 time stamp before \"AFTER RECESS\")?","golden":"1:30 PM (1330)","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"}]},{"eval_id":"019e00b0-60e7-7eb0-ace3-4de6646279c2","probe":"Which members changed their vote from \"yea\" to \"nay\"?","golden":"Ms. Ross, Mrs. Foushee, Mr. Raskin, and Mr. Krishnamoorthi","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi\n"},{"run_index":1,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi\n"},{"run_index":2,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi\n"},{"run_index":3,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi\n"},{"run_index":4,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, Krishnamoorthi\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":6,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":7,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":8,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":9,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":10,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":11,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":12,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":13,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":14,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":15,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":16,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":17,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":18,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":19,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":20,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":21,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":22,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":23,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":24,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":25,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":26,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":27,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":28,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":29,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"}]},{"eval_id":"019e00b5-3554-76cc-805e-ff8228bfefae","probe":"What was the rollcall vote number for the vote on Amendment No. 8?","golden":"Rollcall Vote No. 6 Leg.","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"}]},{"eval_id":"019e00b6-0ba2-731c-a9ed-436b1a7ef320","probe":"What was the rollcall vote number for the vote on S. 5?","golden":"Rollcall Vote No. 7 Leg.","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"}]},{"eval_id":"019e051b-f048-7557-907e-87bf1f5319e0","probe":"What was the rollcall vote number for the Driscoll nomination?","golden":"Rollcall Vote No. 90 Ex.","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"}]},{"eval_id":"019e054b-b654-74aa-b2b0-ad19e229a916","probe":"What is the preferred alternative immunomodulator listed for hospitalized patients requiring HFNC oxygen or NIV?","golden":"IV tocilizumab (Blla)","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"}]},{"eval_id":"019e05ac-b930-79c4-93f6-be96e504477e","probe":"Within how many months of a recent SARS-CoV-2 infection may substantial immunity be conferred, according to footnote b?","golden":"3-6 months","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"}]},{"eval_id":"019e05e7-ce2c-772c-8efd-a4776364273c","probe":"What is the figure number for the blood pressure image?","golden":"Figure 1.0","png_sha":"4fb66d797829b4efe7d38ed6d367871d6664885f70ef83a42d3f0dfec31552e6","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"}]},{"eval_id":"019e0a6f-0c3e-7520-884b-307d309c1b4b","probe":"What percentage of the human body is oxygen?","golden":"65.0%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"}]},{"eval_id":"019e0a70-2afd-7288-98b1-ce3d3fbfaa95","probe":"What percentage of the human body is calcium?","golden":"1.5%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"}]},{"eval_id":"019e0a70-8117-7662-8777-c2511bc6f2ee","probe":"What percentage of the human body is phosphorus?","golden":"1.0%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"}]},{"eval_id":"019e0a71-574c-7f62-97db-97525ad2820e","probe":"What is the figure number for the two models of atomic structure?","golden":"Figure 2.1.2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"}]},{"eval_id":"019e0a76-b33e-7648-8be4-ced32e601bf5","probe":"What element is shown in the planetary model?","golden":"Helium (He)","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"}]},{"eval_id":"019e0a9d-62f1-726d-9b24-bbeb2b85b199","probe":"According to the caption of Figure 3.1.5, which side of the membrane (left or right) shows the hypertonic solution?","golden":"the right side","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":6,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":7,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":8,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":9,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":10,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":11,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":12,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":13,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":14,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":15,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":16,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":17,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":18,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":19,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":20,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":21,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":22,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":23,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":24,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":25,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":26,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":27,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":28,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":29,"verdict":3,"source":"precedent","note":"article handling","answer":"right"}]},{"eval_id":"019e0ad4-4005-7307-aae9-78e3049f1a65","probe":"What are the three lines that pluripotent embryonic stem cells differentiate into?","golden":"Endoderm, Mesoderm, and Ectoderm","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm\n"},{"run_index":1,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm\n"},{"run_index":2,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm\n"},{"run_index":3,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm\n"},{"run_index":4,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":6,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":7,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":8,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":9,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":10,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":11,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":12,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":13,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":14,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":15,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":16,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":17,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":18,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":19,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":20,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":21,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":22,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":23,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":24,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":25,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":26,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":27,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":28,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":29,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"}]},{"eval_id":"019e0ed2-1e72-7fe1-94ee-e4dcffb88ace","probe":"In figure (a), what body part is gripping the pencil?","golden":"a hand","png_sha":"294a4958d5ff0d4328b9ea9e75f13bb4f7ef1d09ee59316db09945f970fa281f","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"hand\n"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"hand\n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"hand\n"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"hand\n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"hand\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":6,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":7,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":8,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":9,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":10,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":11,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":12,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":13,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":14,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":15,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":16,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":17,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":18,"verdict":3,"source":"human","note":"answer expanded","answer":"hand (loosely held)"},{"run_index":19,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":20,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":21,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":22,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":23,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":24,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":25,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":26,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":27,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":28,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":29,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"}]},{"eval_id":"019e0ede-f3cd-7412-8c25-2e079510e6e7","probe":"What is the unit shown on the y-axis label?","golden":"mV (millivolts)","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"}]},{"eval_id":"019e0eea-1322-709e-b1c1-430100607e7d","probe":"In panel (c), what four products come OUT of cellular respiration?","golden":"ATP, Heat, CO\u2082, H\u2082O","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"}]},{"eval_id":"019e0eea-ac39-7b97-941e-8c1e0a744ae3","probe":"In panel (c), what additional input enters the mitochondria from above (with a downward arrow)?","golden":"O\u2082 (oxygen)","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"O2\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"O2\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"O2\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"O2\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"O2\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"}]},{"eval_id":"019de200-d4c1-76bf-b140-f4b73e70f7ed","probe":"What is the maximum sound level (in dBA) allowed for vacuum cleaners?","golden":"70dBA","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"70\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"70\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"70\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"70"}]},{"eval_id":"019de200-d505-7a87-bf67-4ac7fc6b2fd3","probe":"How many days before policy expiration must original copies of policies be delivered to Landlord?","golden":"fifteen (15) days","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"}]},{"eval_id":"019de200-d514-76a5-be6d-0713d4261c08","probe":"What is the full deadline (both time of day and number of business days) by which a Notice of Borrowing must be delivered before a proposed borrowing?","golden":"1:00 p.m. (Eastern time) two (2) Business Days prior","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"}]},{"eval_id":"019de200-d518-778a-9421-02c7d2e3a05a","probe":"What is the section number for 'Time is of the Essence'?","golden":"Section 1.4","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"}]},{"eval_id":"019de740-e7d8-75d0-835d-3a79745c66cc","probe":"How many consecutive Business Days after Landlord's receipt of the Untenantability Notice are required (in non-Force Majeure cases)?","golden":"five (5)","png_sha":"658d8ecfa29b1c0cf9870b2d1c622a5cff7347859e7674b418cc4660be4eb7b9","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019e003d-d1bc-7fb0-a78b-4b79600f8252","probe":"Who is the Custodian of Funds?","golden":"Brad Lander, Comptroller of the City of New York","png_sha":"89c77daf9c6f881f0116f445cbf736cffc12698b60a93b437699a1a075b00138","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":7,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":16,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":24,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":26,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"}]},{"eval_id":"019e00a7-39d7-723b-9490-eca9ac160ad7","probe":"What time did the House reconvene after recess?","golden":"1:30 p.m.","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m.\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m.\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m.\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m.\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."},{"run_index":6,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."},{"run_index":9,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":10,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":11,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."},{"run_index":13,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."},{"run_index":16,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."},{"run_index":18,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."},{"run_index":21,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":22,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":23,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."},{"run_index":25,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":26,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."},{"run_index":28,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."}]},{"eval_id":"019e00b0-cecb-7e7c-8149-7640c1dad861","probe":"Which member changed their vote from \"nay\" to \"yea\"?","golden":"Mr. Palmer","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER\n"},{"run_index":1,"verdict":3,"source":"human","note":"title/honorific handling","answer":"PALMER\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER\n"},{"run_index":4,"verdict":3,"source":"human","note":"title/honorific handling","answer":"PALMER\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":6,"verdict":3,"source":"human","note":"title/honorific handling","answer":"PALMER"},{"run_index":7,"verdict":3,"source":"human","note":"title/honorific handling","answer":"PALMER"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":9,"verdict":3,"source":"human","note":"title/honorific handling","answer":"PALMER"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":18,"verdict":3,"source":"human","note":"title/honorific handling","answer":"PALMER"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":25,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Palmer"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":27,"verdict":3,"source":"human","note":"title/honorific handling","answer":"PALMER"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"}]},{"eval_id":"019e05b5-b5f0-7a24-b00b-652882db4074","probe":"What plateau pressure does the Panel recommend targeting?","golden":"<30 cm H2O","png_sha":"f2687af1be946044a236b7f11f8cf6f728ef1c4e9e442378d2a6ad846b6a54e4","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"}]},{"eval_id":"019e0a77-09dc-7990-a971-9e556b040d8c","probe":"What symbol is used to label the electron in the planetary model?","golden":"e\u2212","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"}]},{"eval_id":"019e0a9e-aa0f-7a55-89e3-a0cd7f73e21f","probe":"What chemical formula is shown next to each red blood cell in the bottom row of Figure 3.1.6?","golden":"H2O","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"}]},{"eval_id":"019e0ac6-e7e3-7800-ac52-eee064e4e8b7","probe":"What is the scale bar length shown in the microscope images?","golden":"5 \u03bcm","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"}]},{"eval_id":"019e0ed1-c40b-7515-aa9e-86ffff7a7b0a","probe":"In figure (a), labeled \"Loosely held,\" what object is being held?","golden":"a pencil","png_sha":"294a4958d5ff0d4328b9ea9e75f13bb4f7ef1d09ee59316db09945f970fa281f","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":6,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":7,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":8,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":10,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":11,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":12,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":13,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":14,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":15,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":16,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":18,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":19,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":20,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":21,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":22,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":23,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":24,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":25,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":27,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":28,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":29,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"}]},{"eval_id":"019de200-d48b-7a0c-9e79-d846c27a96b5","probe":"What page does Article XI Security Deposit start on?","golden":"50","png_sha":"625ba89847b64383ae07efde4a0b7374c88fd2b6dcff552df6812dad32d03160","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"}]},{"eval_id":"019de200-d48c-70ff-b28a-a9c240e3486b","probe":"Who is the landlord named on this office lease?","golden":"Lanham Office 2015 LLC","png_sha":"625ba89847b64383ae07efde4a0b7374c88fd2b6dcff552df6812dad32d03160","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"}]},{"eval_id":"019de200-d48d-703c-b522-b34424519003","probe":"What is Exhibit L?","golden":"Competitor List","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"}]},{"eval_id":"019de200-d48e-767a-b928-9b2d12086653","probe":"What is Exhibit H?","golden":"Roof Access Agreement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"}]},{"eval_id":"019de200-d48f-7596-abf5-cacd23054c4d","probe":"What is Exhibit J?","golden":"Parking Easement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"}]},{"eval_id":"019de200-d490-71ff-a39d-ee962a11796e","probe":"What is Exhibit D?","golden":"Certificate Affirming the Must Take Commencement Date","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"}]},{"eval_id":"019de200-d491-71d6-875d-4fa564623978","probe":"What is Exhibit B?","golden":"Work Agreement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"}]},{"eval_id":"019de200-d492-726b-87fc-5718790d5ebd","probe":"What is Exhibit E?","golden":"Measurement Schedule","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"}]},{"eval_id":"019de200-d493-74c3-af46-0469929cc88d","probe":"What is the Tenant Notice Address?","golden":"8201 Corporate Drive, Suite 900, Landover, MD 20785","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"}]},{"eval_id":"019de200-d494-73d8-930e-be33d26373fa","probe":"What section is referenced for the definition of 'Tax Benefits'?","golden":"Section 5.6","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"}]},{"eval_id":"019de200-d495-7bf0-9c87-96d57c098e71","probe":"What section is referenced for the definition of 'Threshold Successors'?","golden":"Section 10.1","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"}]},{"eval_id":"019de200-d496-74b2-a2cc-5c7a6982836d","probe":"What is the Tenant Notice Address suite number?","golden":"Suite 900","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"}]},{"eval_id":"019de200-d497-758c-9ad2-fceee7efd1fa","probe":"What section is referenced for the definition of 'Tenant's Plans'?","golden":"Section 9.4(a)","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"}]},{"eval_id":"019de200-d498-741d-b3e0-3374c9b02dfc","probe":"What is the title of section H?","golden":"Tenant Modular Furniture","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"}]},{"eval_id":"019de200-d499-74c0-a9b3-74b464fcf74b","probe":"What is the color name listed for the carpet base?","golden":"503 Ginger","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"}]},{"eval_id":"019de200-d49a-7b22-8b95-3fe120b21efc","probe":"What is the section number for the CARPET section?","golden":"09680","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"}]},{"eval_id":"019de200-d49b-76ae-aecb-69e6ba967a73","probe":"What is the section number for the PAINTING section?","golden":"09900","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"}]},{"eval_id":"019de200-d49c-75ca-963f-0649d0c70719","probe":"What is the section number for ACOUSTICAL CEILING?","golden":"09510","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"}]},{"eval_id":"019de200-d49d-7cee-91a2-4ed07626e90a","probe":"What is the name of the company shown in the schedule heading on this page?","golden":"Acadia Realty Trust","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"}]},{"eval_id":"019de200-d49e-7120-8c57-be2e37f1a894","probe":"What is the page number shown at the bottom of the upper section of this page?","golden":"166","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"}]},{"eval_id":"019de200-d49f-72ce-9b9d-97ba16d5640c","probe":"What is the depreciation period (useful life in years) listed in the rightmost column for every property on this page?","golden":"40 years","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"}]},{"eval_id":"019de200-d4a0-7403-856e-aa22d2bdae81","probe":"What is the name of the company shown at the top of the page?","golden":"Acceleron Pharma Inc.","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."}]},{"eval_id":"019de200-d4a1-7f82-aa55-38eac3b9b487","probe":"What is the total deferred tax assets for 2017 (in thousands)?","golden":"145,657","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$145,657\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$145,657"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$145,657"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"}]},{"eval_id":"019de200-d4a2-7a39-91ad-766fdf7c2010","probe":"What is the page number shown at the bottom center of the page?","golden":"F-29","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"}]},{"eval_id":"019de200-d4a3-7518-9715-cc1bb9edb084","probe":"What is the deferred revenue amount for 2016 (in thousands)?","golden":"1,666","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"}]},{"eval_id":"019de200-d4a4-7cca-a0e9-a3ce81d8b684","probe":"What is the federal income tax expense at the statutory rate for 2015?","golden":"34.0%","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"}]},{"eval_id":"019de200-d4a5-753e-87a5-2c51cb711be4","probe":"What is the Research and development credits amount for 2017 (in thousands)?","golden":"12,548","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"}]},{"eval_id":"019de200-d4a6-72d4-b715-3cd7f42e4f66","probe":"What is the State income tax, net of federal benefit percentage for 2016?","golden":"5.9%","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"}]},{"eval_id":"019de200-d4a7-74af-afa8-d3ad189499cc","probe":"What is the deposit amount mentioned in this document?","golden":"$500,000.00","png_sha":"5a5e3841491b2b356eb9b963e45419183ebf6ffae298e69a6f9dd5488bc23e1c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"}]},{"eval_id":"019de200-d4a8-7bdc-bc00-d50a60d60dcc","probe":"What is the title of section 16?","golden":"Mutual Waiver of Subrogation Rights","png_sha":"674a83793665d045c76513a816f7fc9099c52baccd94af7ee817a5f89cdc81d5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"}]},{"eval_id":"019de200-d4a9-7107-917d-4d1e160c26b3","probe":"What is the anticipated commencement date?","golden":"March 1, 2016","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"}]},{"eval_id":"019de200-d4aa-7225-85f5-76e6b1382af9","probe":"What is the premises address?","golden":"2665 North First Street, Suite 300, San Jose, California 95134","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"}]},{"eval_id":"019de200-d4ab-727c-ae0c-07bdc5f94836","probe":"What is the tenant's trade name?","golden":"8x8, Inc.","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."}]},{"eval_id":"019de200-d4ac-742d-b65a-74bd92f2893d","probe":"What is the name of the broker listed in Section 31?","golden":"Cresa Global, Inc.","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."}]},{"eval_id":"019de200-d4ad-71b2-aae9-616c2d5fdb91","probe":"What is the title of Section 33?","golden":"Holding Over","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"}]},{"eval_id":"019de200-d4ae-7bb5-8e56-dfba0d289a6a","probe":"What is the title of Section 38?","golden":"Miscellaneous","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"}]},{"eval_id":"019de200-d4af-7ae9-9bf2-f9ad2d8f5ea5","probe":"What is the title of Section 32?","golden":"Estoppel Certificate","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"}]},{"eval_id":"019de200-d4b0-7068-9693-c265751b0823","probe":"What is the title of Section 34?","golden":"Assignment and Subletting","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"}]},{"eval_id":"019de200-d4b1-72c3-a2c1-2ee5369782dd","probe":"What is the title of Section 31?","golden":"Broker's Commissions","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"}]},{"eval_id":"019de200-d4b2-7946-80ee-a29424252d23","probe":"What is the title of section 14.3?","golden":"Transfer Premium","png_sha":"cde4659cf5512e2c7b127af66eb4bab815dcc533bb04fce540d6d56b21cbb6cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"}]},{"eval_id":"019de200-d4b3-7330-8b3a-3010528a30fa","probe":"What is the title of section 14.5?","golden":"Effect of Transfer","png_sha":"cde4659cf5512e2c7b127af66eb4bab815dcc533bb04fce540d6d56b21cbb6cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"}]},{"eval_id":"019de200-d4b4-702e-932f-bb5b6dbb2b20","probe":"What is the title of Article XXIX?","golden":"Expansion Rights","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"}]},{"eval_id":"019de200-d4b5-709e-9897-f8440e2a964f","probe":"What is the title of Article XXX?","golden":"METROPLEX II ASSUMPTION","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"}]},{"eval_id":"019de200-d4b6-73e9-aa56-a2eb7119541a","probe":"What is the title of Section 29.1?","golden":"Right of First Refusal","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"}]},{"eval_id":"019de200-d4b7-7604-b550-db1d11ebef12","probe":"What is the title of Section 28.2?","golden":"Additional Amenities","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"}]},{"eval_id":"019de200-d4b8-7164-91b2-3ec03d9f397f","probe":"What is the title of section 12?","golden":"Severance Payments","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"}]},{"eval_id":"019de200-d4b9-723f-8a38-4f373e93bffa","probe":"What is the title of section 13?","golden":"Certain Covenants of the Executive","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"}]},{"eval_id":"019de200-d4bb-7ca6-ada6-5158e0ca9947","probe":"What is the item number for the Foreperson/Day Porter Executive dress shirt?","golden":"#828","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"}]},{"eval_id":"019de200-d4bc-76fc-9589-06797f38e895","probe":"What is the title of section E?","golden":"UNIFORMS","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"}]},{"eval_id":"019de200-d4bd-7e20-a10a-47c622032b52","probe":"What is the item number for the women's Pleated Dress Pants?","golden":"#596","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"}]},{"eval_id":"019de200-d4be-7e4d-b5ce-bf5d0d9e3745","probe":"What is the title of section J?","golden":"LIGHTING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"}]},{"eval_id":"019de200-d4bf-7a42-91f9-d00fe759f635","probe":"What is the title of section H?","golden":"SECURITY AND INCIDENT REPORTING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"}]},{"eval_id":"019de200-d4c0-7843-8047-cc09e991e12b","probe":"What is the title of section K?","golden":"GREEN CLEANING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"}]},{"eval_id":"019de200-d4c2-7ad3-88a8-ed0b24b345b7","probe":"What is the item number for the men's Foreperson/Day Porter Pleated dress pants?","golden":"#865","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"}]},{"eval_id":"019de200-d4c3-7771-b087-cb7f248214a4","probe":"What is the item number listed for the women's Long Sleeve Dress Blouse?","golden":"#528","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"}]},{"eval_id":"019de200-d4c4-736b-b432-833199724c46","probe":"What is the title of section 24.0?","golden":"HOLDOVER","png_sha":"214b816ecbf747322726d54a0cb92edd6d184be6a6e04656e532d637c65eda11","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"}]},{"eval_id":"019de200-d4c5-7b98-9a5a-c76d5fb5ae1e","probe":"What is the title of section 5.2?","golden":"Operating Expenses; Consumable Expenses and Base Building Expenses","png_sha":"3343506981bd41f08b63b8df40f8ba763e2bc1566a850d0903f24b1c5782cf77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"}]},{"eval_id":"019de200-d4c6-7729-866a-8ac3402457fb","probe":"What is the title of Article XIV?","golden":"Assignment and Subletting","png_sha":"d8fa233fb12db1beef1e4088d39215700d5884c2d4cb968b6985c6febde8a2ca","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"}]},{"eval_id":"019de200-d4c7-7305-82b7-76d4d75e7f9d","probe":"What is the title of Article XIII?","golden":"Condemnation","png_sha":"d8fa233fb12db1beef1e4088d39215700d5884c2d4cb968b6985c6febde8a2ca","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"}]},{"eval_id":"019de200-d4c8-787c-9ed4-e33640efb435","probe":"What is the title of Article 28?","golden":"Confidentiality","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"}]},{"eval_id":"019de200-d4c9-7b7f-9e32-c47d4f1c0b0e","probe":"What is the title of Exhibit D?","golden":"Form of Deed","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"}]},{"eval_id":"019de200-d4ca-7805-9cc9-6e26cd367bbc","probe":"What is the title of Article 25?","golden":"Waiver of Jury Trial","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"}]},{"eval_id":"019de200-d4cb-70dc-a225-ac7807b5a70c","probe":"What is the title of Article 33?","golden":"Costs and Attorneys' Fees","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"}]},{"eval_id":"019de200-d4cc-7013-9323-c4a463e49255","probe":"What is the Lessor's telephone number listed in the notices section?","golden":"(81) 8358.7978","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"}]},{"eval_id":"019de200-d4cd-7c1a-a4b1-fd5dc2875413","probe":"What is the title of section 24.4?","golden":"Captions","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"}]},{"eval_id":"019de200-d4ce-73b9-b787-b0f7568e7018","probe":"What is the Lessee's telephone number listed in the notices section?","golden":"(81) 8158.8800","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"}]},{"eval_id":"019de200-d4cf-7e95-8f4b-cca6ed5396ce","probe":"What is the title of section 24.5?","golden":"Severability","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"}]},{"eval_id":"019de200-d4d0-7008-bd98-2d410f1fb7fa","probe":"What is the name of the person to contact for the Lessor in the notices section?","golden":"Mr. Juan Carlos Gonzalez Quezada","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"}]},{"eval_id":"019de200-d4d1-7e39-92cb-dc82b006e040","probe":"What is the title of section 24.1?","golden":"Brokers","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"}]},{"eval_id":"019de200-d4d2-7ff3-ae3f-b7ce26ebedc4","probe":"What is the title of section 22.3?","golden":"Labor","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"}]},{"eval_id":"019de200-d4d3-7a72-9dfe-0011bce8efc8","probe":"What is the maximum tenant improvement allowance amount in dollars?","golden":"$559,160.00","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"}]},{"eval_id":"019de200-d4d4-7185-bf69-9197f90e27ce","probe":"What is the title of Section II?","golden":"TENANT'S WORK","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"}]},{"eval_id":"019de200-d4d5-7ac3-8e4e-c758cbae290a","probe":"What is the per square foot dollar amount mentioned for the Allowance?","golden":"$40.00","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"}]},{"eval_id":"019de200-d4d6-77e1-9296-5f9e11cf7728","probe":"What does item (c) say?","golden":"Intentionally deleted.","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."}]},{"eval_id":"019de200-d4d7-71ee-b89a-13f57933c5ed","probe":"What is the company name shown in the headers of the financial statements?","golden":"Acadia Realty Trust and Subsidiaries","png_sha":"d99abf4bae64753a77c680d1e83acdbdc08eb377e9da9bc0a4af8337f67971e2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"}]},{"eval_id":"019de200-d4d8-73df-b318-56c93e913a1d","probe":"What is the rent payable for December 2016 in the Metroplex Rent table?","golden":"137,399","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"}]},{"eval_id":"019de200-d4d9-7080-91a1-8e4024ae5b27","probe":"What is the title of Exhibit M?","golden":"Metroplex Rent","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"}]},{"eval_id":"019de200-d4da-740b-af0a-30cdbbdc3a00","probe":"What is the rent payable for July 2018?","golden":"145,763","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"}]},{"eval_id":"019de200-d4db-76f8-b9cf-eb901aaef607","probe":"What is the title of Exhibit N?","golden":"Exclusions From Operating Expenses","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"}]},{"eval_id":"019de200-d4dc-76d9-b19c-2bb2f2c2d455","probe":"What is the rent payable for March 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4dd-7a8e-97e8-6cbb97c9f288","probe":"What is the rent payable for January 2018?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4de-7510-a1bb-a2200cf532b1","probe":"What is the rent payable for May 2018?","golden":"145,763","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"}]},{"eval_id":"019de200-d4df-72db-b8e2-5470717b76c7","probe":"What is the rent payable for September 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4e0-7497-8998-04b404a57589","probe":"What is listed as item (i) under Excluded Expenses in Exhibit N?","golden":"Real Estate Taxes","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"}]},{"eval_id":"019de200-d4e1-704d-bad7-731b3da45bdf","probe":"What is the rent payable for November 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4e2-7aab-ae79-29c74e645fca","probe":"What is the title of Exhibit C?","golden":"Technology Exhibit","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"}]},{"eval_id":"019de200-d4e3-7937-8135-40c4b4f0cb8e","probe":"What is the markup percentage on outgoing mail?","golden":"10%","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"}]},{"eval_id":"019de200-d4e4-7765-86d5-d5fb371119ed","probe":"What is the title of Exhibit B?","golden":"Summit Billing Information","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"}]},{"eval_id":"019de200-d4e5-7bb2-9e8d-5d17eac142de","probe":"What is the reconnection fee per hour mentioned in Exhibit C?","golden":"$100","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"}]},{"eval_id":"019de200-d4e6-7499-90b0-274586c057d5","probe":"What are the standard business hours listed for Summit's remedial maintenance?","golden":"9:00 am to 5:00 pm, Monday - Friday","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"}]},{"eval_id":"019de200-d4e7-7aba-997b-697fce37c98b","probe":"Who signed as Chief Executive Officer of 1847 Holdings LLC?","golden":"Ellery W. Roberts","png_sha":"17421f00db7e68e09f420ba5abd403a8bc79b47f8f380327515bff5297f38fed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"}]},{"eval_id":"019de200-d4e8-7f62-96ae-519b14f37f5f","probe":"On what day of December 2024 did the Guarantors execute this Guaranty?","golden":"13th","png_sha":"17421f00db7e68e09f420ba5abd403a8bc79b47f8f380327515bff5297f38fed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"}]},{"eval_id":"019de200-d4e9-71c2-9557-1e2c70c1e1fb","probe":"What is the Per RSF Base Rent for the Initial Term?","golden":"$20.50","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"}]},{"eval_id":"019de200-d4ea-7529-926e-f6d2957fdefe","probe":"Who is the Named Tenant?","golden":"2U Harkins Road LLC","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"}]},{"eval_id":"019de200-d4eb-7ccd-933d-0af15a613cf0","probe":"What is the Alteration Threshold dollar amount?","golden":"$200,000.00","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"}]},{"eval_id":"019de200-d4ec-7fff-aceb-46c812561273","probe":"Which floors of the Building are designated as the Must Take Expansion Premises?","golden":"Floors 5, 6 and 7","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"}]},{"eval_id":"019de200-d4ed-7a5a-bca1-903c35b0c671","probe":"What is the speed limit mentioned in rule 4 of the parking rules?","golden":"5 miles per hour","png_sha":"4a35d25bb27a032bf2661265ea4187cfc0129b1d6aa4a12ae16fc6380aea8e4c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"}]},{"eval_id":"019de200-d4ee-76cd-96ee-560ea13db477","probe":"What are the parking hours listed in rule 1?","golden":"7:30 a.m. to 6:30 p.m., Monday through Friday","png_sha":"4a35d25bb27a032bf2661265ea4187cfc0129b1d6aa4a12ae16fc6380aea8e4c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"}]},{"eval_id":"019de200-d4ef-7bf8-a7ba-27307744e3f9","probe":"What is the 2nd Floor Build-Out Allowance amount?","golden":"$600,000.00","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"}]},{"eval_id":"019de200-d4f0-7baf-9b58-1e08027b6f0d","probe":"How many RSF is the 2nd Floor Premises calculated as for Base Rent purposes?","golden":"12,000 RSF","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"}]},{"eval_id":"019de200-d4f2-7a99-af6e-94a36878aec2","probe":"What is the per-RSF dollar amount used to calculate the Must Take Allowance?","golden":"$46.50","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"}]},{"eval_id":"019de200-d4f3-7347-815c-24a4e9f82950","probe":"In the example, what is the Must Take Allowance for the 7th floor?","golden":"$1,198,611.65","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"}]},{"eval_id":"019de200-d4f4-7dcb-9449-8179714e49d7","probe":"What is the limit of liability for Landlord's commercial general liability insurance?","golden":"$5,000,000 per occurrence","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"}]},{"eval_id":"019de200-d4f5-78f3-8340-3580046edcc8","probe":"What is the each occurrence limit for Personal Injury Liability?","golden":"$9,000,000","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"}]},{"eval_id":"019de200-d4f6-7741-884c-42611e27bcef","probe":"What is the Insured's participation percentage for Personal Injury Liability?","golden":"0%","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"}]},{"eval_id":"019de200-d4f7-7940-b10a-9822b81b3272","probe":"What is the Lobby Renovations Allowance?","golden":"$500,000.00","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"}]},{"eval_id":"019de200-d4f8-7a38-8a19-517016d4b55b","probe":"What is the Initial Build-Out Allowance per RSF?","golden":"$48.00","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"}]},{"eval_id":"019de200-d4f9-7748-a94b-9e4c68688de5","probe":"What is the construction supervision fee percentage Landlord charges on hard construction costs?","golden":"1%","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"}]},{"eval_id":"019de200-d4fa-70fc-b7a8-b9c26c2b14e0","probe":"By what date must Tenant substantially complete the 2nd Floor Build-Out Work?","golden":"April 1, 2018","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"}]},{"eval_id":"019de200-d4fb-7f01-8927-c6d175a34ace","probe":"By what date must Tenant substantially complete the Initial Build-Out Work of the Initial Premises?","golden":"April 1, 2017","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"}]},{"eval_id":"019de200-d4fc-7cca-908f-984e3d8120e7","probe":"What is the umbrella liability each occurrence amount?","golden":"$5,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"}]},{"eval_id":"019de200-d4fd-74c2-abb8-1bb3a38e217c","probe":"What is the medical payments coverage amount?","golden":"$5,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"}]},{"eval_id":"019de200-d4fe-76cb-bdd6-bb011389179c","probe":"What is the fire damage legal liability coverage amount?","golden":"$50,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"}]},{"eval_id":"019de200-d4ff-7fd5-9027-7197160465a2","probe":"What is the automobile liability combined single limit amount?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d500-7cfe-8ff2-d8bbbb64073a","probe":"What is the bodily injury by accident coverage amount per accident under Workers' Compensation Coverage B?","golden":"$500,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"}]},{"eval_id":"019de200-d501-782d-845b-a4e35e143c20","probe":"What is the combined single limit per occurrence for Coverage A under Commercial General Liability?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d502-7a8b-9ba6-c9892e2eeecc","probe":"What insurance form is the general liability insurance to be written on?","golden":"2001 Insurance Services Office form","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"}]},{"eval_id":"019de200-d503-798a-afa1-45a2677f34db","probe":"What is the personal and advertising injury liability (Coverage B) amount?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d504-70ea-9d31-b199175fed3c","probe":"In what geographic area must business interruption insurance match amounts customarily carried by responsible tenants?","golden":"Greater Boston","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"}]},{"eval_id":"019de200-d506-744e-be70-a75cf629bab5","probe":"What is the non-refundable assignment/sublease review fee?","golden":"$1,500","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"}]},{"eval_id":"019de200-d509-782f-8cb5-81249701c47f","probe":"What percentage of the excess must Tenant pay to Landlord as Assignment/Sublease Excess Rent?","golden":"100%","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"}]},{"eval_id":"019de200-d50a-7a93-8a69-a34202f99ee3","probe":"What is the term used for the portion of Premises eliminated under the Elimination Period?","golden":"Eliminated Space","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"}]},{"eval_id":"019de200-d50b-714d-a6f0-8fbb3c33bc67","probe":"What is the term defined for the date immediately prior to the effective date of the proposed assignment?","golden":"Earlier Termination Date","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"}]},{"eval_id":"019de200-d50c-743d-ad76-780e2c2fb12d","probe":"What is the term used for the period after the Elimination Period during which the Eliminated Space is restored to the Premises?","golden":"Restoration Period","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"}]},{"eval_id":"019de200-d50d-7c5f-a9f2-1705d2b33bc2","probe":"What is the term defined for the consideration payable by the assignee or subtenant?","golden":"Assignment/Sublease Consideration","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"}]},{"eval_id":"019de200-d50f-730f-bba3-567d098ebd36","probe":"By what time each weekday must the stainless steel tops on the 18th Street light boxes be wiped down?","golden":"8:00 AM","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"}]},{"eval_id":"019de200-d510-7320-b95d-f545ed219bc5","probe":"How often must window frames and ledges be swept with a soft-bristled brush on the building exterior?","golden":"Monthly","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"}]},{"eval_id":"019de200-d511-7272-9565-2412f58e253c","probe":"How often must service area floors be dust mopped, at minimum?","golden":"Once per week","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"}]},{"eval_id":"019de200-d512-7496-808b-5b1ea05ca3f8","probe":"How often must standpipe fire hose connections on the exterior of the building be cleaned and polished?","golden":"Weekly","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"}]},{"eval_id":"019de200-d513-7149-ae8c-e8a7754d572b","probe":"What is the minimum amount for a partial prepayment of Revolving Loans?","golden":"$100,000","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"}]},{"eval_id":"019de200-d516-7459-9245-cc659422a55c","probe":"By what time on the Termination Date must the entire outstanding principal of each Revolving Loan be paid?","golden":"12:00 Noon (Eastern time)","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"}]},{"eval_id":"019de200-d517-7577-ad4f-c469f0a5f3e3","probe":"What is the higher integral multiple required for partial prepayments of Revolving Loans?","golden":"$25,000","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"}]},{"eval_id":"019de200-d519-76a9-b52e-17fb3cd3da08","probe":"What rate do Revolving Loans accrue interest at, plus the Applicable Margin?","golden":"LIBOR Rate","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"}]},{"eval_id":"019de200-d51a-7cbd-841b-aa945ef2b4a8","probe":"Notices of Borrowing must be delivered before what time (Eastern time)?","golden":"1:00 p.m.","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."}]},{"eval_id":"019de200-d51b-7404-9feb-b6384f640f1a","probe":"How many calendar days prior to lease termination must the parties allow Lessor to enter the property for inspection?","golden":"60","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"}]},{"eval_id":"019de200-d51c-7dd7-ad07-e2fd96baf505","probe":"Who conducted the Phase I Environmental Assessment mentioned in section 11.1?","golden":"GAIM REGIOMONTANA","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"}]},{"eval_id":"019de200-d51d-7bbb-9bed-8ceaca14c398","probe":"What is the telephone number listed for Mr. Juan Carlos Gonzalez Quezada?","golden":"(81) 8358.7978","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"}]},{"eval_id":"019de200-d51e-7caf-b475-352d47499736","probe":"What is the postal code (C.P.) listed in the address for Mr. Juan Carlos Gonzalez Quezada?","golden":"66220","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"}]},{"eval_id":"019de200-d51f-723d-9741-37784d76009a","probe":"What is the telephone number listed for Mr. David Rodriguez Santos at Torre Sienna?","golden":"(81) 8356.1200","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"}]},{"eval_id":"019de200-d520-7d78-a11e-ce881c0ff357","probe":"How many calendar days does Lessor have to object to a proposed sublease in writing?","golden":"30","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"}]},{"eval_id":"019de200-d521-77a9-8367-9a4a834e7041","probe":"What is the apartment/interior number (Int.) listed in the address for Torre Sienna?","golden":"1403","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"}]},{"eval_id":"019de200-d522-7ac9-8bba-7b83fb15043b","probe":"What exhibit is the 'Maintenance Carnet' attached as?","golden":"Exhibit \"J\"","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""}]},{"eval_id":"019de200-d524-75fd-bff6-f429befeae8a","probe":"How many calendar days does Lessee have to dispute damages or Alterations indicated in Lessor's notice?","golden":"15","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"}]},{"eval_id":"019de22d-8775-7482-9f31-5e7710938d70","probe":"What is the original principal amount of the 3.50% Series A Convertible Senior Notes due February 1, 2018?","golden":"$70.3 million","png_sha":"9999d442e3243c2ea48a7de6c4c9b162568b4e59e41492087837bdb419a11d2c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"}]},{"eval_id":"019de778-2487-7ceb-942f-bbc9cce683b5","probe":"What is the public law number?","golden":"118-109","png_sha":"a0300e50b30b31b24996ac843a50187dca0d8e81f6c026161ae3e07159e9815a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"}]},{"eval_id":"019dfae7-e8c3-7289-a5e3-25d26a497795","probe":"What is the fiscal year end date?","golden":"September 28, 2024","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"}]},{"eval_id":"019dfae8-2c75-7590-9083-4c07bf26944a","probe":"What is the Commission File Number?","golden":"001-36743","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"}]},{"eval_id":"019dfae8-8300-75b0-98f0-558c886fd068","probe":"What is the registrant's telephone number?","golden":"(408) 996-1010","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"}]},{"eval_id":"019dfae8-d37e-73db-bad0-7dbbebba1d87","probe":"What is the IRS Employer Identification Number?","golden":"94-2404110","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"}]},{"eval_id":"019dfae9-3119-7c26-b2ed-73fb2888fdfe","probe":"What is the par value per share of Apple's common stock?","golden":"$0.00001","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"}]},{"eval_id":"019dfae9-c244-75c3-92a8-4f02d64471e6","probe":"What were Americas net sales in 2024 (in millions)?","golden":"$167,045","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"}]},{"eval_id":"019dfaea-1b4b-7bef-bf30-f8f1ee1cb9d6","probe":"What were Europe net sales in 2024 (in millions)?","golden":"$101,328","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"}]},{"eval_id":"019dfaea-c282-7bca-85d8-a2edb7306504","probe":"What were total net sales in 2024 (in millions)?","golden":"$391,035","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"}]},{"eval_id":"019dfaeb-1b0e-7077-a093-a8a138a79e25","probe":"What were Greater China net sales in 2022 (in millions)?","golden":"$74,200","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"}]},{"eval_id":"019dfaec-3d80-7c7c-95b7-6a34a086d48b","probe":"What is the date the report was signed?","golden":"November 1, 2024","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"}]},{"eval_id":"019dfaec-8345-7eea-8840-6867945a7a06","probe":"Who is the Director and Chair of the Board?","golden":"Arthur D. Levinson","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"}]},{"eval_id":"019dfaec-e961-7051-a4ce-b66996997cb2","probe":"Who is the Senior Director of Corporate Accounting?","golden":"Chris Kondo","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"}]},{"eval_id":"019dfaed-c27e-7590-9034-1cc2a5319b55","probe":"Who is the accounting firm that signed this consent?","golden":"Ernst & Young LLP","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"}]},{"eval_id":"019dfaee-6467-74cc-8101-5271bea3e394","probe":"What is the Form S-8 number for the Apple Inc. Employee Stock Purchase Plan?","golden":"333-203698","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"}]},{"eval_id":"019dfaf0-11d2-70d1-be50-371940478750","probe":"Where is Braeburn Capital, Inc. incorporated?","golden":"Nevada, U.S.","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."}]},{"eval_id":"019dfaf0-52d8-7941-b336-19bfbe7f8bc1","probe":"Where is Apple Asia Limited incorporated?","golden":"Hong Kong","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"}]},{"eval_id":"019dfaf1-05a1-718d-818a-e45ba4945ba1","probe":"Where is Apple Operations Mexico, S.A. de C.V. incorporated?","golden":"Mexico","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"}]},{"eval_id":"019dfaf2-2642-7eae-b1fb-1620be9706bc","probe":"Starting on what date does this policy apply to Incentive-Based Compensation that is Received?","golden":"October 2, 2023","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"}]},{"eval_id":"019dfaf3-1977-7337-8a56-6b3d55edd900","probe":"What Nasdaq listing rule was adopted to implement Rule 10D-1 under the Exchange Act?","golden":"Listing Rule 5608","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"}]},{"eval_id":"019dfaf3-d93a-7e7a-8293-bed401dc3c74","probe":"Under what year's Securities and Exchange Act is 'executive officer' defined for this policy?","golden":"1934","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"}]},{"eval_id":"019dfaf4-6d06-7bb4-9da0-5703eced16ad","probe":"What company's logo appears at the top of this policy?","golden":"Apple","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"}]},{"eval_id":"019dfaf5-67bd-727d-92f0-43a3108e55cf","probe":"What is the commission file number?","golden":"001-37580","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"}]},{"eval_id":"019dfaf5-e414-73d4-a5bb-864069d83389","probe":"What is the IRS Employer Identification Number?","golden":"61-1767919","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"}]},{"eval_id":"019dfaf6-3c67-7437-b33f-106a71df96cc","probe":"What is the registrant's telephone number?","golden":"(650) 253-0000","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"}]},{"eval_id":"019dfaf6-8eaf-75f8-a68a-e019cf9ab6dc","probe":"What is the interest rate of the Senior Notes due 2064?","golden":"4.375%","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"}]},{"eval_id":"019dfaf6-cd98-71f2-9576-0e07833ebd70","probe":"What is the interest rate of the Senior Notes due 2028?","golden":"2.375%","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"}]},{"eval_id":"019dfaf7-7376-72e6-af9f-4f0302bf05aa","probe":"What is the trading symbol for Alphabet's Class C Capital Stock?","golden":"GOOG","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"}]},{"eval_id":"019dfaf7-a3e9-7079-abc1-1170e6a73c4f","probe":"What is the fiscal year end date on this 10-K?","golden":"December 31, 2025","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"}]},{"eval_id":"019dfaf8-7549-77d5-b050-b8468d035af7","probe":"What was the total amount of Class C share repurchases for the three months ended March 31, 2025?","golden":"$12,535 million","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"}]},{"eval_id":"019dfaf8-f7e3-7fa2-809d-07b2ec3cfaea","probe":"How much remained available for Class A and Class C share repurchases as of March 31, 2025?","golden":"$29.5 billion","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"}]},{"eval_id":"019dfafa-9cb0-7412-8eac-d16591d94510","probe":"What is the quarterly cash dividend declared on April 2025?","golden":"$0.21","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"}]},{"eval_id":"019dfafb-3912-792d-bc47-54ca00054b5c","probe":"What were the revenues for 2025?","golden":"$402,836 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"}]},{"eval_id":"019dfafb-834e-72a8-893b-436ffbf094a2","probe":"What was the net income for 2024?","golden":"$100,118 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"}]},{"eval_id":"019dfafb-dcbb-70a3-96b4-fcb14e3ee61c","probe":"What was the cost of revenues for 2023?","golden":"$133,332 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"}]},{"eval_id":"019dfafc-94fe-761b-9254-9f753ab96d14","probe":"What was the total amount of share repurchases for the nine months ended September 30, 2025?","golden":"$40,117 million","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"}]},{"eval_id":"019dfafd-0e8d-7a0f-8f4e-4d3d489b698a","probe":"By what percentage did the Board of Directors increase the quarterly cash dividend in April 2025?","golden":"5%","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"}]},{"eval_id":"019dfafe-5a0c-7b21-8bfa-72a257476e5a","probe":"What was the total carrying value of senior unsecured notes outstanding as of September 30, 2025?","golden":"$23.6 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"}]},{"eval_id":"019dfaff-051e-7ba2-8350-09ebbfdb115a","probe":"How much remained available for Class A and Class C share repurchases as of September 30, 2025?","golden":"$74.8 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"}]},{"eval_id":"019dfb00-8129-7fae-9c3d-085f17af7163","probe":"How many Class C shares were repurchased in the three months ended September 30, 2025 (in millions)?","golden":"51","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"}]},{"eval_id":"019dfb01-6670-7c43-bf57-578d4e8743df","probe":"How much was the revolving credit facility expiring in April 2030?","golden":"$6.0 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"}]},{"eval_id":"019dfb02-8211-7651-9ec4-8c0ebcf58a3b","probe":"What was the dollar amount of Class A share repurchases for the three months ended September 30, 2025 (in millions)?","golden":"$926","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926"}]},{"eval_id":"019dfb06-2d63-7e40-9cfc-442adddd3a61","probe":"As of what date did the CEO and CFO conclude on the disclosure controls evaluation?","golden":"June 30, 2025","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"}]},{"eval_id":"019dfb06-7255-7580-9ef1-58f24ae75626","probe":"What rule under the Exchange Act was used to evaluate disclosure controls and procedures?","golden":"Rule 13a-15","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"}]},{"eval_id":"019dfb07-58e1-741b-95ae-39f6ad5b9738","probe":"For what quarter ended date is the internal control reporting statement made?","golden":"June 30, 2025","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"}]},{"eval_id":"019dfb08-723b-72c9-8209-4c6b104c74d9","probe":"What form is the Quarterly Report on?","golden":"Form 10-Q","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"}]},{"eval_id":"019dfb09-b2b4-7900-94d0-5ead62b5fa3a","probe":"How much was the initial investment used in the graph comparison?","golden":"$100","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"}]},{"eval_id":"019dfb0a-1542-7607-afff-3824643328be","probe":"On what date does the graph's tracking period end?","golden":"December 31, 2025","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"}]},{"eval_id":"019dfb0a-4250-7161-8e90-fa2502ad8254","probe":"What is the starting date of the graph's tracking period?","golden":"December 31, 2020","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"}]},{"eval_id":"019dfb0a-bbec-7b6d-bb26-274ff05f9459","probe":"What is the highest dollar value shown on the y-axis of the graph?","golden":"$400","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"}]},{"eval_id":"019dfb0a-e54b-7973-8d05-99144d938deb","probe":"What color is the line representing the S&P 500 in the graph?","golden":"Green","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"}]},{"eval_id":"019dfb0b-0fe9-717a-b315-903647d9114e","probe":"What color is the line representing Alphabet Inc. Class C in the graph?","golden":"Red","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"}]},{"eval_id":"019dfb0b-9664-7b20-bea5-647276953368","probe":"How much is Alphabet acquiring Wiz, Inc. for?","golden":"$32.0 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"}]},{"eval_id":"019dfb0c-07a8-768c-bf46-7d82769ad116","probe":"What is the long-term income taxes payable as of December 31, 2025?","golden":"$9.5 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"}]},{"eval_id":"019dfb0d-123a-74db-8a55-4a162b6b8cfb","probe":"How much is Alphabet acquiring Intersect for in cash?","golden":"$4.8 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"}]},{"eval_id":"019dfb0d-98a6-7573-8987-ba32c57f6b7a","probe":"What is the total amount of purchase commitments and other contractual obligations as of December 31, 2025?","golden":"$149.1 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"}]},{"eval_id":"019dfb0e-3ccc-74fa-9d0d-91c2663bea11","probe":"What was the total revenue for the three months ended March 31, 2025?","golden":"$90,234 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"}]},{"eval_id":"019dfb0e-aa32-78f0-b197-81311a562d15","probe":"What were the total long-lived assets in the United States as of March 31, 2025?","golden":"$149,304 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"}]},{"eval_id":"019dfb0f-11dc-7143-87ab-1b18f0a0c5b8","probe":"What was Google Cloud's operating income for the three months ended March 31, 2025?","golden":"$2,177 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"}]},{"eval_id":"019dfb10-1fb2-7986-b06c-55501bbd796e","probe":"What was the United States revenue for the three months ended September 30, 2025?","golden":"$48,758 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"}]},{"eval_id":"019dfb10-c712-7d30-9f15-c857b9160151","probe":"What was the EMEA revenue for the nine months ended September 30, 2025?","golden":"$84,096 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"}]},{"eval_id":"019dfb11-2196-7673-aeb2-eebcf53e53b2","probe":"What was the APAC revenue for the three months ended September 30, 2024?","golden":"$14,547 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"}]},{"eval_id":"019dfb11-8ce1-72d9-b0ab-fc0be563e187","probe":"What were the total revenues for the nine months ended September 30, 2025?","golden":"$289,007 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"}]},{"eval_id":"019dfb14-6817-7cc7-90e2-fce76cd476e7","probe":"How many employees did JPMorganChase have globally as of December 31, 2025?","golden":"318,512","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"}]},{"eval_id":"019dfb14-a085-7b52-8f76-6678f2a4de9c","probe":"How many employees does JPMorganChase have in North America?","golden":"185,208","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"}]},{"eval_id":"019dfb14-f2e3-7cee-a27e-79e81867b37a","probe":"How many employees work in CCB?","golden":"144,196","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"}]},{"eval_id":"019dfb15-3908-7fc5-93bd-052705ae9929","probe":"In how many countries are JPMorganChase's employees located?","golden":"66","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"}]},{"eval_id":"019dfb15-75a7-7c29-a2ca-90c32df63ac5","probe":"What percentage of total employees are women?","golden":"48%","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"}]},{"eval_id":"019dfb15-c7c7-74ee-b29b-e7b5d8c9a152","probe":"How many employees work in the Asia-Pacific region?","golden":"96,499","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"}]},{"eval_id":"019dfb16-cbe3-7d4d-a23d-2234c2d7d297","probe":"What is the first bulleted item under the list of electronic and internet-based financial solutions?","golden":"lending and other extensions of credit to consumers","png_sha":"704943f48019c6bab8cb509e1ddeb6f9b48085007ac9101976ed3d04798ac274","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"}]},{"eval_id":"019dfb18-cb9a-7558-a5ce-7b4911abc1ba","probe":"What was the total assets under management in 2025 (in billions)?","golden":"$4,791","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"}]},{"eval_id":"019dfb19-eada-7639-80c1-d416915f2795","probe":"How many client advisors were there as of December 31, 2025?","golden":"10,150","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"}]},{"eval_id":"019dfb1a-7fed-744e-a7bc-585de30578fb","probe":"What was the equity assets value in 2025 (in billions)?","golden":"$1,400","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"}]},{"eval_id":"019dfb1a-d4b4-7ee1-b950-3f3208c24be4","probe":"What was the reported net interest income in 2025 (in millions)?","golden":"$95,443","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"}]},{"eval_id":"019dfb1b-4a0a-766a-92cd-c2e37df27c36","probe":"What was the net yield on average interest-earning assets on a managed basis in 2025?","golden":"2.50%","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"}]},{"eval_id":"019dfb1b-9e1c-704c-b958-e7a06540c65f","probe":"What was the Memo: Total Markets net revenue in 2025 (in millions)?","golden":"$35,782","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"}]},{"eval_id":"019dfb1c-4c58-739f-8241-e4a688fff415","probe":"What was the noninterest revenue excluding Markets in 2023 (in millions)?","golden":"$44,361","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"}]},{"eval_id":"019dfb1d-0b1b-7540-9211-41f0ac069d15","probe":"In what year was MetLife, Inc. incorporated in Delaware?","golden":"1999","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"}]},{"eval_id":"019dfb1d-fe01-7745-a248-c6531ebdce43","probe":"What act is referenced as the source of the 'forward-looking statements' definition?","golden":"Private Securities Litigation Reform Act of 1995","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"}]},{"eval_id":"019dfb1e-4042-7d24-95d6-9213cb5fb946","probe":"How many factors are listed on this page?","golden":"22","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"}]},{"eval_id":"019dfb1e-d54d-73fd-8f17-16eb21390c86","probe":"What is factor number 10 in the list?","golden":"London Interbank Offered Rate discontinuation and transition to alternative reference rates","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"}]},{"eval_id":"019dfb1f-5f66-79ad-be34-3c4e429dbcac","probe":"How old is Steven J. Goulart?","golden":"64","png_sha":"8a8df5c53ffc88bd982b700c7adc729d6f1a78da7ebcbf1ee0a1a778e2017590","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"}]},{"eval_id":"019dfb20-e27a-7c39-b2f6-4f9d7929ea4e","probe":"What is the estimated fair value of total fixed maturity securities AFS as of December 31, 2022?","golden":"$276,780 million","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"}]},{"eval_id":"019dfb22-1d21-7795-bb3e-bdc661245cb9","probe":"What is the % of Total for Aaa/Aa/A rated securities as of December 31, 2021?","golden":"70.4%","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"}]},{"eval_id":"019dfb23-4f44-7d83-91d3-79100e6cffec","probe":"What were the adjusted earnings available to common shareholders for the U.S. segment?","golden":"$2,996 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"}]},{"eval_id":"019dfb23-8371-717a-825f-6e20e45dcb5f","probe":"What is the U.S. segment's percentage contribution to total segment level adjusted earnings?","golden":"47%","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"}]},{"eval_id":"019dfb23-d976-764b-875f-1c7d8d24b80e","probe":"What were the adjusted earnings for the Asia segment?","golden":"$1,378 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"}]},{"eval_id":"019dfb24-353e-721c-af95-7c83f5c7c811","probe":"What were the adjusted earnings for the EMEA segment?","golden":"$246 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"}]},{"eval_id":"019dfb25-429c-7aee-a55e-43ed0574b742","probe":"What is the estimated fair value of policyholder account balances?","golden":"$115,408 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"}]},{"eval_id":"019dfb25-8392-72a3-af31-c1805d75def2","probe":"What is the estimated fair value of equity securities?","golden":"$1,684 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"}]},{"eval_id":"019dfb26-154c-7462-80c9-ac925ac520e6","probe":"What is the notional amount of foreign currency swaps?","golden":"$56,025 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"}]},{"eval_id":"019dfb29-7d6d-77ed-abe1-9e196503fe98","probe":"What is American Life Insurance Company's Moody's rating?","golden":"A1","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"}]},{"eval_id":"019dfb29-d233-7190-9c54-414c50184509","probe":"What is Metropolitan Life Insurance Company's Fitch rating?","golden":"AA-","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA- (4th of 19)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA- (4th of 19)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA- (4th of 19)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"}]},{"eval_id":"019dfb2a-30eb-73bc-9534-9a1a79fcefd9","probe":"What is Metropolitan Tower Life Insurance Company's Moody's rating?","golden":"Aa3","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"}]},{"eval_id":"019dfb3c-0056-7fd4-8497-80ad7e52deed","probe":"What is the date on the letter?","golden":"September 12, 2025","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"}]},{"eval_id":"019dfb3c-443c-749d-9922-e22f48da574a","probe":"What is the total amount of expenses stated in the letter?","golden":"$537.6 billion","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"}]},{"eval_id":"019dfb3c-e409-7e70-93e0-584a7b66e218","probe":"What is the fax number listed at the bottom of the letter?","golden":"916.322.4404","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"}]},{"eval_id":"019dfb3d-df1d-70c3-8680-871f110c4e18","probe":"How many state departments are involved in the ACFR production, according to the letter?","golden":"more than 200","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"}]},{"eval_id":"019dfb41-090f-742c-a295-a841b0d40942","probe":"What is the last year the ACFR publication target date in March was achieved, according to the letter?","golden":"2018","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"}]},{"eval_id":"019dfb42-0697-72fe-ace9-658c5975fe72","probe":"What is the General fund balance as previously reported on 6/30/2023?","golden":"$64,003,688","png_sha":"4d385e9f1f0ded0edf6cd42e1fce98d308714a9c9a90264d60830da6a87b20a5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"}]},{"eval_id":"019dfb42-9508-70e6-ba0b-e32a83de1982","probe":"What is the Pension/OPEB balance as previously reported on 6/30/2023?","golden":"$826,165,564","png_sha":"4d385e9f1f0ded0edf6cd42e1fce98d308714a9c9a90264d60830da6a87b20a5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"}]},{"eval_id":"019dfb45-009b-71c5-a560-66fa6f28c0b7","probe":"What were the personal income taxes for 2024?","golden":"$116.5 billion","png_sha":"be9e4b96b82c2251ae314ddc72ad643547069399fbff67cb23663b4b60410b07","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"}]},{"eval_id":"019dfb45-c922-797e-8c28-c8e8919e6e6b","probe":"What was the General Fund's ending fund balance for fiscal year 2023-24?","golden":"$63.4 billion","png_sha":"be9e4b96b82c2251ae314ddc72ad643547069399fbff67cb23663b4b60410b07","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"}]},{"eval_id":"019dfb48-c7e6-72a9-8f31-8e936894de0c","probe":"What was the total primary government net position in 2006 (in thousands)?","golden":"$48,552,143","png_sha":"6ded8b72d8724efb0a5addcabb85b9fb055c8702b034b32a8bd9d35ae7b3b2d4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143 thousand\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143 thousand\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143 thousand\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143 thousand\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143 thousand\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"}]},{"eval_id":"019dfb49-36d0-787d-9b10-263d0dc86158","probe":"What was the total business-type activities net position in 2005 (in thousands)?","golden":"$9,638,143","png_sha":"6ded8b72d8724efb0a5addcabb85b9fb055c8702b034b32a8bd9d35ae7b3b2d4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"}]},{"eval_id":"019dfb49-c621-751e-8311-221426895f61","probe":"What date does the fiscal year end?","golden":"June 30, 2013","png_sha":"e78f4e20277a031b7f8a1c8ec01e35359d5db802026c772a280aa46b2e15036d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"}]},{"eval_id":"019dfb4a-c5b5-77b8-8666-73fe5ecf7295","probe":"What word appears on the banner above the figure in the seal?","golden":"EUREKA","png_sha":"e78f4e20277a031b7f8a1c8ec01e35359d5db802026c772a280aa46b2e15036d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"}]},{"eval_id":"019dfb4c-a89f-7747-8ca3-fb374afbe129","probe":"How many employees were in the Services industry in 2012?","golden":"6,219,000","png_sha":"ee102138e4471a718761ff29297490e756f20be442c4eab71f74ad7b88ef9337","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"}]},{"eval_id":"019dfb4d-3d6b-7988-bb66-c81ee4e34bf7","probe":"How many employees were in Manufacturing in 2003?","golden":"1,544,500","png_sha":"ee102138e4471a718761ff29297490e756f20be442c4eab71f74ad7b88ef9337","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"}]},{"eval_id":"019dfff9-bbf0-7f8f-9eeb-4283d498732d","probe":"What is the General Fund amount due from primary government to University of California?","golden":"$169,215","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"}]},{"eval_id":"019dfffa-4c63-71d9-9bae-44bb0f5d067a","probe":"What is the total primary government amount due to component units?","golden":"$209,125","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"}]},{"eval_id":"019dfffa-9fa6-7a63-a87b-53eda9047796","probe":"What is the amount from Nonmajor governmental funds due to University of California?","golden":"36,988","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"}]},{"eval_id":"019dfffb-b244-7a37-903d-2e6addf12282","probe":"What was the net general bonded debt per capita in 2018?","golden":"$2,042","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"}]},{"eval_id":"019dfffc-0d62-7f14-a566-4e70db84b399","probe":"What was the net general bonded debt as a percentage of personal income in 2015?","golden":"4.0%","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"}]},{"eval_id":"019dfffc-678a-79c5-aaea-473c3f22a054","probe":"What was the General obligation bonds amount in 2017?","golden":"$79,503,871","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"}]},{"eval_id":"019dfffc-e4bf-79ad-8c4e-89d704ac54ed","probe":"What is at the top of the Texas government structure chart?","golden":"The Electorate","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"}]},{"eval_id":"019dfffd-a1d4-7a49-94b8-3ef9aa5497d4","probe":"What are the two highest courts shown under the Judicial branch?","golden":"The Supreme Court of Texas and The Court of Criminal Appeals","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"}]},{"eval_id":"019dfffe-6b06-706f-a135-e5934397dcc8","probe":"What body sits directly below the Legislature on the chart, alongside the State Auditor's Office?","golden":"Legislative Committees","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"}]},{"eval_id":"019dffff-131f-7d34-8e0c-2be25da41c0d","probe":"What two courts are shown at the bottom level under County-Level Courts?","golden":"Municipal Courts and Justice of the Peace Courts","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"}]},{"eval_id":"019dffff-a90b-7567-a8fa-d73e11996c14","probe":"What body is shown at the very bottom of the Legislative branch chart?","golden":"Sunset Advisory Commission","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"}]},{"eval_id":"019e0000-52c3-755e-9a98-534e00107784","probe":"What is the total pass-through to other agencies?","golden":"$254,334.30","png_sha":"cee789f33becc6e55d762115a7b119808f36099b5c736f4b0ec740bce52a004c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"}]},{"eval_id":"019e0001-dddd-7fec-b736-f93ff293500f","probe":"What was the balance in the ESF fund on Aug. 31, 2024?","golden":"$23.8 billion","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"}]},{"eval_id":"019e0002-846c-7a5c-bcd2-21cf9dab8b63","probe":"What was the Texas unemployment rate as of November 2024?","golden":"4.2 percent","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"}]},{"eval_id":"019e0003-4dd3-73ec-8ba4-bf652587ad06","probe":"By how much is Texas' population projected to grow in 2025?","golden":"376,600","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"}]},{"eval_id":"019e0008-27fa-70f4-8421-41777f7bcace","probe":"What office is shown in pink under the First Deputy Mayor?","golden":"Office of Efficiency","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"}]},{"eval_id":"019e0009-2f8e-768d-8762-ff9e82bcea2b","probe":"What is the SAO Report Number?","golden":"25-316","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"}]},{"eval_id":"019e0009-af38-766a-9ac7-cb0908ad2999","probe":"What percent of the assets of the Colleges and Universities does the University of Texas System constitute?","golden":"72.9 percent","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"}]},{"eval_id":"019e000a-7052-7138-b0db-733f874d02cd","probe":"What percent of the expenditures for the State Highway Fund does the Texas Department of Transportation constitute?","golden":"99.9 percent","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"}]},{"eval_id":"019e000b-d49b-7660-82c4-81ecfb04a236","probe":"What percentage of revenue comes from Charges for Services in Graph MDA-6?","golden":"59.7%","png_sha":"3f8e2c78a2134ddb79f740cc731c989a29e5b11d89cdb0254e1f1740d44cfdb0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"}]},{"eval_id":"019e000d-e61a-7a45-b84f-1c881c74e271","probe":"What is the fair value of Private Equity investments (in thousands)?","golden":"$76,309,756","png_sha":"1993d56fb3f7471f5844aa6a62bb8dd9a43b4784dac30f107664bca458bf68ea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"}]},{"eval_id":"019e000e-f859-77f7-aa7c-927c51e130e8","probe":"What is the unfunded commitment for Energy, Natural Resources, Infrastructure (in thousands)?","golden":"$11,460,123","png_sha":"1993d56fb3f7471f5844aa6a62bb8dd9a43b4784dac30f107664bca458bf68ea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"}]},{"eval_id":"019e0010-c825-72aa-a139-0e4ab295b2dc","probe":"What is the minimum aggregate floor area required by the CEP program?","golden":"25,000 square feet","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"}]},{"eval_id":"019e0011-2a92-7ac7-89be-ac4f2296baea","probe":"Under the CRP/CEP programs, by how much were the City's tax revenues reduced in 2024 (in thousands)?","golden":"$12,500","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"}]},{"eval_id":"019e0011-cff1-7126-8235-02b26f0fbab9","probe":"What year did ICAP replace ICIP?","golden":"2008","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"}]},{"eval_id":"019e0017-450f-737d-a346-38c48007c835","probe":"Under the CRP program, what is the per-square-foot dollar amount used in the base abatement calculation formula?","golden":"$2.50","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"}]},{"eval_id":"019e0018-17a0-7847-a0b3-11f039bc48a6","probe":"What is the page number shown at the bottom of this page?","golden":"128","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"}]},{"eval_id":"019e0019-d170-7146-8e38-cc44276e6018","probe":"Under the CRP/CEP programs, by how much were the City's tax revenues reduced as a result of abatement agreement in 2024 (in thousands)?","golden":"$12,500","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"}]},{"eval_id":"019e001b-3183-79f1-a745-4e066a6ce3ef","probe":"What is the Executive Order number mentioned in the letter?","golden":"2025-1","png_sha":"781c6fcbd4f3164179bf71cd942ca2e9794fc7c49c6bbcf883dd13f2ce626331","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"}]},{"eval_id":"019e001b-77bc-7c11-843b-51dfbbec15c3","probe":"Who signed this letter?","golden":"Mayor Brandon Johnson","png_sha":"781c6fcbd4f3164179bf71cd942ca2e9794fc7c49c6bbcf883dd13f2ce626331","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"}]},{"eval_id":"019e001d-d405-7881-ab8b-abcb0d7e70e1","probe":"What is Deloitte's fax number listed on the page?","golden":"+1 312 486 1486","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"}]},{"eval_id":"019e001f-f83d-78ad-bad5-21b87bdb9833","probe":"According to the auditor's report, the Pension Trust Funds represent what percentages of the assets, financial position, and revenues respectively?","golden":"92%, 100%, and 72%","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"}]},{"eval_id":"019e0020-bffb-7733-931f-63dac6e0f8f0","probe":"Who is the report addressed to as Mayor?","golden":"Brandon Johnson","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"}]},{"eval_id":"019e0027-f41a-7a7a-b3f6-f9b59cde341b","probe":"What is the experience study period for the Policemen's plan?","golden":"January 1, 2019 - December 31, 2023","png_sha":"2aded5f520cbaa023e8d0c1e94f15e68ccafa9f34d1e6736781e6f894512fe8e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"}]},{"eval_id":"019e0028-b45f-7292-959c-f04db8d08d19","probe":"What is the experience study period for the Laborers' plan?","golden":"January 1, 2017 - December 31, 2019","png_sha":"2aded5f520cbaa023e8d0c1e94f15e68ccafa9f34d1e6736781e6f894512fe8e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"}]},{"eval_id":"019e002a-8546-75d0-9290-e4f34687786f","probe":"What year ended is referenced at the top of the page?","golden":"December 31, 2024","png_sha":"4ceaa28bf7551920a1890b7fbf19a27b1cc875ad22828548d20d5021ffb4cb9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"}]},{"eval_id":"019e002e-34d1-7c51-ba48-bffeca76fb26","probe":"What was the loans receivable balance of the CCCF as of December 31, 2024?","golden":"$3.1 million","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"}]},{"eval_id":"019e002e-ef48-7527-8160-cb77c6e44245","probe":"On what date did the City of Chicago City Council adopt the ordinance organizing the STSC?","golden":"October 11, 2017","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"}]},{"eval_id":"019e0030-d1da-7720-bec1-d70663e3456a","probe":"On what date did the City Council adopt the CCCF Ordinance?","golden":"November 16, 2016","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"}]},{"eval_id":"019e0033-8f40-79d7-8505-50112ded8060","probe":"What is the website where complete financial statements of the STSC can be obtained?","golden":"www.salestaxsecuritizationcorporation.com","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"}]},{"eval_id":"019e003a-5da3-7d08-9f15-665248ccb0cf","probe":"What was the final budgeted Vehicle Tax amount under Transportation Tax (in thousands)?","golden":"$128,777","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"}]},{"eval_id":"019e003a-e619-7c9f-b4b2-aa2807d3bff9","probe":"What was the actual Motor Fuel Tax and Project revenue under Transportation Tax (in thousands)?","golden":"$122,483","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"}]},{"eval_id":"019e003c-6cc9-782c-bca0-875bef94c76c","probe":"What was the final budgeted MEABF Pension Reserve under Special Area and Utility Taxes (in thousands)?","golden":"$216,275","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"}]},{"eval_id":"019e003d-55d2-7007-b3b6-dc37892643d2","probe":"Who is the Chief Actuary?","golden":"Marek Tyszkiewicz","png_sha":"89c77daf9c6f881f0116f445cbf736cffc12698b60a93b437699a1a075b00138","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"}]},{"eval_id":"019e003f-44df-7a8d-a15c-ff2dc3cf553b","probe":"What is the funded ratio for the 2022 valuation date?","golden":"85.1%","png_sha":"13c08f8d02fa78d2fc1f1b9783d494af4a43f3083f75509ffac06a9ae415320f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"}]},{"eval_id":"019e0040-0266-795a-b6d2-549f195f8032","probe":"What percentage of the Police Superior Officers' Variable Supplements Fund is held in Collective Trust Funds?","golden":"59.28%","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"}]},{"eval_id":"019e0040-6668-7abd-8cd8-dd05d069c1c1","probe":"What is the dollar amount of Equity Securities in the Police Officers' Variable Supplements Fund?","golden":"$771,119","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"}]},{"eval_id":"019e0041-2237-71d4-8880-cb8564c7b0ae","probe":"What is the dollar amount of Short-Term Investments in the Police Superior Officers' Variable Supplements Fund?","golden":"$8,441","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"}]},{"eval_id":"019e0042-1c07-71d9-8683-e990abab4862","probe":"What is the Reduced Service Retirement probability at 20 years of service?","golden":"5.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"}]},{"eval_id":"019e0043-db39-746e-8a90-d9b8e9e16e2f","probe":"What is the Unreduced Before Full Escalation probability at 22 years of service?","golden":"5.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"}]},{"eval_id":"019e0044-11fe-7039-99f0-4014e1cca342","probe":"What is the Reduced Service Retirement probability at 21 years of service?","golden":"2.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"}]},{"eval_id":"019e0045-18ce-7ff9-90d3-7a8a76d3a7b2","probe":"What is the As Restated Total Liabilities amount?","golden":"54,689,670","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"}]},{"eval_id":"019e0046-8a1d-76f7-a894-dfdf17c5e779","probe":"What is the As Previously Stated Unrestricted (Deficit) amount (in thousands of dollars)?","golden":"(33,888,893)","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"}]},{"eval_id":"019e0048-5d8d-7e41-bfac-807538f6bc7d","probe":"What is the required year of adoption for GASB Statement No. 102?","golden":"2025","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"}]},{"eval_id":"019e0049-7334-7204-a87d-cdd77f11d1df","probe":"What is the As Restated Total Net (Deficit)/Position amount (in thousands)?","golden":"$(30,877,248)","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"}]},{"eval_id":"019e004a-3183-7f93-ae28-888547cf9f69","probe":"What is the As Previously Stated Accrued and Other Liabilities amount (in thousands)?","golden":"$2,037,352","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"}]},{"eval_id":"019e004b-c349-7e93-af8d-24a8c0227413","probe":"Who is the Chairman of the Texas Transportation Commission?","golden":"J. Bruce Bugg, Jr.","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."}]},{"eval_id":"019e004c-1788-7c26-832d-effce8fee9e9","probe":"What city is Commissioner Robert C. Vaughn from?","golden":"Dallas","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"}]},{"eval_id":"019e004c-7b29-737b-b3c2-4cb5677b686a","probe":"What city is Commissioner Steven D. Alvis from?","golden":"Houston","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"}]},{"eval_id":"019e004e-6fac-7e8f-a9ed-7aab75af118d","probe":"What is the Total Foreign Currency Risk for Fiduciary Funds (in thousands)?","golden":"$454,100","png_sha":"14dd94971a85d5333d42a72d87ae42c4f4cf19684f10114f6d12e3dc0dcfbba3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"}]},{"eval_id":"019e004f-570b-7494-b4dc-1980043719cb","probe":"What is the Component Units amount for Uninsured and Uncollateralized in Table 3A (in thousands)?","golden":"$729,847","png_sha":"14dd94971a85d5333d42a72d87ae42c4f4cf19684f10114f6d12e3dc0dcfbba3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"}]},{"eval_id":"019e0050-7b43-7b4a-b132-8ba0d44ecc08","probe":"What is the Total Fund Balance \u2013 Governmental Funds (in thousands)?","golden":"$98,174,085","png_sha":"2e5b15b0fe9ca40f66bc4f99fea40f7e0fb26c9abe4ac75ea6dad2ab72ae36d6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"}]},{"eval_id":"019e007c-e48c-710f-9404-90a2a810ccb4","probe":"What is the Net Position of Governmental Activities (in thousands)?","golden":"$134,878,410","png_sha":"2e5b15b0fe9ca40f66bc4f99fea40f7e0fb26c9abe4ac75ea6dad2ab72ae36d6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"}]},{"eval_id":"019e007d-9a24-752a-89d4-7fe852700caa","probe":"What is the total revenue shown in the Revenue by Source pie chart?","golden":"$190.5 Billion","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"}]},{"eval_id":"019e007d-e19f-7d15-815d-b4e94383d99b","probe":"What are the total expenses for Health and Human Services?","golden":"$75,194 million","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"}]},{"eval_id":"019e007e-1a80-7e4b-98c2-9c3f2d812c06","probe":"What percentage of revenue came from Taxes?","golden":"42.7%","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"}]},{"eval_id":"019e007e-5b89-72a2-b531-375ac7e4ca75","probe":"What is the dollar amount of Operating Grants and Contributions?","golden":"$74.9 billion","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"}]},{"eval_id":"019e007e-aac9-7785-8c44-edb9f9dfe20d","probe":"What are the total expenses across all governmental activities?","golden":"$154,896","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"}]},{"eval_id":"019e007f-3589-7306-b64b-6253528585e4","probe":"What page is Risk Factors on?","golden":"14","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"}]},{"eval_id":"019e007f-7683-7d10-a251-ff6bdde0aca0","probe":"What page is Executive Compensation on?","golden":"105","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"}]},{"eval_id":"019e007f-b345-710c-b63d-5812e55e82ef","probe":"What page is Financial Statements and Supplementary Data on?","golden":"48","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"}]},{"eval_id":"019e0080-81ba-7bac-bba1-8cc2e8324436","probe":"What page is the Budgetary Comparison \u2013 General Fund on?","golden":"47","png_sha":"0a460adc7db810670c579dc36d27c02a4097bb3e02f77fbbeacd84bbcc9d2f0e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"}]},{"eval_id":"019e0080-b0bf-7f30-a02e-a2ed8dcea371","probe":"What page is the Schedule of Employee Benefits \u2013 All Funds on?","golden":"56","png_sha":"0a460adc7db810670c579dc36d27c02a4097bb3e02f77fbbeacd84bbcc9d2f0e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"}]},{"eval_id":"019e0081-ed0a-7c3a-a9ba-53b6b5920008","probe":"What word is shown as a watermark across the map?","golden":"DRAFT","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"}]},{"eval_id":"019e0082-3d98-723b-b6b4-132e744dab15","probe":"Which county is labeled at the bottom-right area of the map, below Ellis?","golden":"Navarro","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"}]},{"eval_id":"019e0083-0a96-77f4-a106-fb583482c798","probe":"How much did the General Land Office (GLO) increase?","golden":"$860 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"}]},{"eval_id":"019e0083-5461-7354-8851-9512e63b1c22","probe":"How much did the Texas Commission on Environmental Quality (TCEQ) increase?","golden":"$543 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"}]},{"eval_id":"019e0083-c942-7b97-83f8-c0423a20e2a4","probe":"How much did the Federal Emergency Management Agency (FEMA) decrease?","golden":"$420 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"}]},{"eval_id":"019e0084-65de-77d8-92f6-79df23bc1fad","probe":"What is the phone number for Pattillo, Brown & Hill, L.L.P.?","golden":"254.772.4901","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"}]},{"eval_id":"019e0084-dffc-7ecf-b0c1-44b81836ebdd","probe":"What is the date of the year ended for the audit?","golden":"September 30, 2024","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"}]},{"eval_id":"019e009f-5030-795d-b32e-68b8c8725b1a","probe":"What is the page number shown at the bottom right?","golden":"H261","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"}]},{"eval_id":"019e00a0-6d47-7a01-8cdb-9db00cf90181","probe":"Which bill number is referenced as the 'Born-Alive Abortion Survivors Protection Act'?","golden":"H.R. 21","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"}]},{"eval_id":"019e00a1-03cf-7de0-9353-8ede1f29d21e","probe":"What time did the House meet?","golden":"10 a.m.","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."}]},{"eval_id":"019e00a2-46eb-7c4d-93dc-be4b015c5931","probe":"Until what time may morning-hour debate continue?","golden":"11:50 a.m.","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."}]},{"eval_id":"019e00a2-8827-7350-ac1d-d1e691c7bc93","probe":"Which Congress's proceedings does this issue cover?","golden":"119th","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"}]},{"eval_id":"019e00a3-4654-7104-90ff-d36264aea63f","probe":"Who did Speaker Mike Johnson appoint as Speaker pro tempore for the day?","golden":"Nathaniel Moran","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"}]},{"eval_id":"019e00a4-39cf-73f5-a08d-bdaf6f0e9555","probe":"Which state is Mrs. Trahan from?","golden":"Massachusetts","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"}]},{"eval_id":"019e00a4-9927-7270-b177-688639d2d84a","probe":"Which state is Mr. Thompson from?","golden":"Pennsylvania","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"}]},{"eval_id":"019e00a5-86fd-7ef3-9421-534e8a66b6ef","probe":"How many 'yeas' were there in Roll No. 20?","golden":"214","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"}]},{"eval_id":"019e00a5-ff31-72d6-b137-910bed3336e6","probe":"How many representatives were 'not voting' in Roll No. 20?","golden":"15","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"}]},{"eval_id":"019e00a6-329c-73a0-9a01-cd95583196e9","probe":"How many 'nays' were there in Roll No. 20?","golden":"204","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"}]},{"eval_id":"019e00a7-701e-7774-bdaa-4a60fe45e545","probe":"What is the page number shown at the top left?","golden":"H276","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"}]},{"eval_id":"019e00a7-fb7c-797d-8520-954d5503a748","probe":"What is the Roll number for the vote shown on this page?","golden":"20","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"}]},{"eval_id":"019e00ac-04dd-7f1d-bcec-9be7f5c1f3ce","probe":"Did Aderholt vote yea or nay?","golden":"yea","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"}]},{"eval_id":"019e00ac-a893-7e85-9fc2-0de0e7d020dd","probe":"Did Cherfilus-McCormick vote yea or nay?","golden":"nay","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"}]},{"eval_id":"019e00ad-32af-76df-9057-a199ce91dd17","probe":"How many \"Garcia\" members are listed in the NAYS column?","golden":"3","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"}]},{"eval_id":"019e00ad-d3ed-7216-853a-30e02dbd1131","probe":"Who is the first name listed alphabetically in the NAYS column?","golden":"Adams","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"}]},{"eval_id":"019e00ae-10e5-7c6b-956c-c30654f0adda","probe":"What is the last name listed in the YEAS column?","golden":"Zinke","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"}]},{"eval_id":"019e00b3-c235-73fb-ba21-0118c8eadbf3","probe":"What is the page number shown in the top-left corner?","golden":"S250","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"}]},{"eval_id":"019e00b4-9c27-73de-8223-11187c914c6f","probe":"What is the date shown at the top-right of the page?","golden":"January 20, 2025","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"}]},{"eval_id":"019e00b9-b13c-7e4a-bf11-475eea29d6d3","probe":"Did Senator McConnell vote yea or nay on the final passage of S. 5?","golden":"yea","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"}]},{"eval_id":"019e00bb-59ee-702a-8cec-38e372b26db8","probe":"How many senators voted YEA on Amendment No. 8?","golden":"75","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"}]},{"eval_id":"019e00bb-a83a-79e5-808d-25352081e864","probe":"How many senators voted NAY on the final passage of S. 5?","golden":"35","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"}]},{"eval_id":"019e00bc-df61-7504-ab8f-56af050077d7","probe":"Who is being considered for Secretary of State on Executive Calendar No. 2?","golden":"Marco Rubio","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"}]},{"eval_id":"019e00bf-a471-719a-84c8-972702dced95","probe":"What dollar amount is mentioned as the threshold for financial harm to a State or its residents?","golden":"$100","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"}]},{"eval_id":"019e00c1-687b-7e30-917e-677d5c514e5a","probe":"Who asked for the yeas and nays on the vote for S. 5?","golden":"Mrs. Britt","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"}]},{"eval_id":"019e00c1-d9d4-7426-9471-e13471bf2c6f","probe":"How many nays were there on the vote on Amendment No. 8?","golden":"24","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"}]},{"eval_id":"019e00c6-1e73-73ec-8e95-413c88e39426","probe":"How much did the Wesley Hunt Victory Fund contribute on 2/3/2025?","golden":"$25,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"}]},{"eval_id":"019e00c6-5871-7da2-a93b-3aefb5c66f16","probe":"What is the page number shown at the top left?","golden":"S2714","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"}]},{"eval_id":"019e00c8-3f2a-7e4f-b0e4-86c796356894","probe":"How much did the Connecticut Republican State Central Committee transfer on 9/27/2024?","golden":"$10,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"}]},{"eval_id":"019e00c9-4d63-7e78-a3b2-fd24f554e0db","probe":"What was the largest single contribution amount listed in the Spouse section?","golden":"$25,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"}]},{"eval_id":"019e00c9-c213-7e12-b66f-043b2559c706","probe":"Who is being nominated to be Lieutenant Commander in the Coast Guard?","golden":"John O. Mansolillo","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"}]},{"eval_id":"019e00ce-9d49-7844-bd6c-346e75c0b284","probe":"What is the bill number for the bill to direct the Secretary of the Treasury to stop minting the penny?","golden":"S. 1525","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"}]},{"eval_id":"019e0518-b40f-7b97-99f0-2cd141711ff0","probe":"What is the bill number for the bill to regulate assault weapons?","golden":"S. 1531","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"}]},{"eval_id":"019e051c-6f18-78b3-a1d7-9d8a0a2b9618","probe":"How many senators voted yea on the Driscoll nomination?","golden":"66","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"}]},{"eval_id":"019e051d-3c27-7462-be35-0be6eece26b9","probe":"How many senators were listed as NOT VOTING?","golden":"6","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"}]},{"eval_id":"019e051d-a887-715d-88bf-933cc563b087","probe":"How many nays were there in the vote?","golden":"28","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"}]},{"eval_id":"019e051e-38d3-7d68-9805-50585c912e12","probe":"How would Senator Cruz of Texas have voted if present?","golden":"yea","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"}]},{"eval_id":"019e051f-e004-7dd8-b253-949abd5846ae","probe":"Who is Jess Andrews leaving to work for, according to Senator Kennedy's tribute?","golden":"the new Senator from Ohio","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"}]},{"eval_id":"019e0520-1d4b-7483-9ed6-1c012178bbd9","probe":"How many years has Jess Andrews run Senator Kennedy's communications shop?","golden":"5 years","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"}]},{"eval_id":"019e0520-d920-72fd-9146-7ff4401c225d","probe":"Did Senator Booker vote yea or nay on the Driscoll nomination?","golden":"nay","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"}]},{"eval_id":"019e0523-07a2-7eed-a522-32a019057e4b","probe":"Under what clause and rule were sponsors added to public bills?","golden":"clause 7 of rule XII","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"}]},{"eval_id":"019e0524-a11c-7139-bf9b-71cd8bf76e24","probe":"Who was added as a sponsor to H.R. 247?","golden":"Ms. Omar","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"}]},{"eval_id":"019e0525-2888-7fab-bbe4-24c066ee419f","probe":"Who was added as a sponsor to H.R. 31?","golden":"Mr. Stauber","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"}]},{"eval_id":"019e0529-5749-7c17-9f42-70fde0a280ae","probe":"Who was added as a sponsor to H.R. 438?","golden":"Ms. Malliotakis","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"}]},{"eval_id":"019e0529-ab42-7f49-b945-e7fa7946e4e8","probe":"Who was added as a sponsor to H.R. 493?","golden":"Ms. DelBene","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"}]},{"eval_id":"019e053e-4d48-7017-b80c-96993dddb76d","probe":"How many patients were in the SOC alone group?","golden":"4,321","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"}]},{"eval_id":"019e053f-1f3f-7cd4-9bdf-bb8319b59261","probe":"What is the table number and title?","golden":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"}]},{"eval_id":"019e0540-facb-7b6a-8fd8-3f509341da68","probe":"What was the mean age of participants in the RECOVERY trial?","golden":"66 years","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"}]},{"eval_id":"019e0541-5acc-73a2-a0f0-4a8a3fd3f3d7","probe":"When was this table last updated?","golden":"February 29, 2024","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"}]},{"eval_id":"019e0542-7270-77f1-aa19-55066dadd841","probe":"How many patients were in the SOC alone group?","golden":"4,321","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"}]},{"eval_id":"019e0543-15cb-749c-890f-dc25b546fa1f","probe":"What percentage of participants had laboratory-confirmed SARS-CoV-2 infection?","golden":"89%","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"}]},{"eval_id":"019e0547-98af-7c91-aa30-6a7096eca524","probe":"What is the table number and title shown at the top of the page?","golden":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"}]},{"eval_id":"019e0547-eecc-7d07-95de-24c48450b6a5","probe":"On what date was this document downloaded according to the bottom of the page?","golden":"3/1/2024","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"}]},{"eval_id":"019e0549-117f-704c-b2ed-3771bcbf57de","probe":"What is the URL shown at the bottom of the page where this document was downloaded from?","golden":"https://www.covid19treatmentguidelines.nih.gov/","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"}]},{"eval_id":"019e054a-48f1-7ae1-8c9a-f98de9d0fa5b","probe":"What is the recommendation for patients hospitalized but not requiring supplemental oxygen who are at high risk of progressing to severe COVID-19?","golden":"Remdesivir","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"}]},{"eval_id":"019e0550-1990-7266-9919-560f19c4cee5","probe":"In the CATCO trial, what percentage of patients received corticosteroids?","golden":"87%","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"}]},{"eval_id":"019e0550-c523-7e3c-a7bb-5e58b208e5dc","probe":"In the CATCO trial, what percentage of patients were on conventional oxygen?","golden":"54%","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"}]},{"eval_id":"019e0553-86d1-71ca-b900-5bbaabb7ca45","probe":"How many randomized controlled trials were included in the pooled analysis of individual data mentioned with ACTT-1?","golden":"9","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"}]},{"eval_id":"019e0555-7910-7ed7-a44b-456f65b6a4b0","probe":"Approximately what fraction of patients in the Solidarity trial received corticosteroids?","golden":"two-thirds","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"}]},{"eval_id":"019e055a-07af-77a5-89c9-42e3d3fa137d","probe":"What is the maximum daily dose of low-dose aspirin?","golden":"81 mg","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"}]},{"eval_id":"019e055a-a680-7323-8d08-3ac187ccf89f","probe":"What is the rating for IVIG monotherapy when glucocorticoids are contraindicated?","golden":"BIIb","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"}]},{"eval_id":"019e055d-286a-7563-a7e4-fcf6471dab8b","probe":"What is the dose of infliximab listed for intensification therapy?","golden":"5\u201310 mg/kg IV for 1 dose","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"}]},{"eval_id":"019e055e-28ea-7f76-943f-b37787cd73cb","probe":"What is the IV dose range for high-dose anakinra?","golden":"5\u201310 mg/kg/day","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"}]},{"eval_id":"019e055f-16e9-7882-9aa1-55c4030f9893","probe":"According to footnote c, in which patients should infliximab NOT be used?","golden":"patients with macrophage activation syndrome","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"}]},{"eval_id":"019e055f-c91a-7e0f-9401-67c36bb17b91","probe":"According to the Key, what does CAA stand for?","golden":"coronary artery aneurysm","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"}]},{"eval_id":"019e0561-73ca-7c46-9bf0-5c643e61cde3","probe":"What does IBW stand for according to the Key?","golden":"ideal body weight","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"}]},{"eval_id":"019e05a7-e018-7ce5-b33f-396e12ec5cd7","probe":"What is the risk level for moderately or severely immunocompromised patients regardless of vaccination status?","golden":"High","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"}]},{"eval_id":"019e05a9-4840-7d85-a06e-f789e706a095","probe":"What is the risk level for patients with mild asthma, overweight, or well-controlled diabetes?","golden":"Low","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"}]},{"eval_id":"019e05ab-8ba2-7ab7-87ce-36b3ba6a8e47","probe":"What is the risk level shown for patients with sickle cell disease or chronic kidney disease?","golden":"Intermediate","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"}]},{"eval_id":"019e05ad-fd6c-7734-88ed-1ec50c394ff9","probe":"How many conditions are listed under \"Strong or Consistent Association With Progression to Severe COVID-19\"?","golden":"8","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"}]},{"eval_id":"019e05b0-6eee-79fe-9c1a-85e69f5d1b78","probe":"What is the page number?","golden":"174","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"}]},{"eval_id":"019e05b0-9f88-7493-8093-1faf321a65c1","probe":"What is the date the document was downloaded?","golden":"3/1/2024","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"}]},{"eval_id":"019e05b0-d9cd-707e-a8fc-05816b33e002","probe":"What is the title of this section shown in the orange header?","golden":"Summary Recommendations, continued","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"}]},{"eval_id":"019e05b1-edb1-71fd-a8f1-178c8ce2372a","probe":"How many hours per day of prone ventilation does the Panel recommend?","golden":"12 to 16 hours","png_sha":"f2687af1be946044a236b7f11f8cf6f728ef1c4e9e442378d2a6ad846b6a54e4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"}]},{"eval_id":"019e05ba-b872-7e8f-9ab0-ebf540496835","probe":"How many people were in the placebo group?","golden":"761","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"}]},{"eval_id":"019e05bd-b79d-79ce-83a2-61bee82f41bd","probe":"What was the mean age of participants?","golden":"58 years","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"}]},{"eval_id":"019e05bd-fce1-7c37-9985-6a2be13c70b5","probe":"What percentage of participants received corticosteroids?","golden":"79%","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"}]},{"eval_id":"019e05bf-8d4e-7984-b130-f857ef177151","probe":"What is Pablo Tebas's financial disclosure relationship with Shionogi?","golden":"Consultant","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"}]},{"eval_id":"019e05c0-2875-7f53-8cd2-1afd5c604eef","probe":"What is Andrew T. Pavia's relationship with Haleon?","golden":"Honoraria","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"}]},{"eval_id":"019e05c1-9d7a-7ef6-8d4a-75d9a4d8bc53","probe":"What is Grant Schulert's financial disclosure relationship with Boehringer Ingelheim?","golden":"Consultant","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"}]},{"eval_id":"019e05c2-9694-7119-b6c6-e2863ab93d51","probe":"What company is Phyllis Tien disclosed as receiving research support from?","golden":"Merck","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"}]},{"eval_id":"019e05c3-4ee4-7de9-abf1-e04c45c9b57f","probe":"What is Susan Swindells's financial disclosure relationship with GSK/ViiV Healthcare?","golden":"Research support","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"}]},{"eval_id":"019e05e7-8068-7743-a656-13b1d4d4190b","probe":"How many chapter objectives are listed on this page?","golden":"5","png_sha":"4fb66d797829b4efe7d38ed6d367871d6664885f70ef83a42d3f0dfec31552e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e05e9-158a-7e0b-a377-74df9d26138b","probe":"How many abdominal regions are shown in figure (a)?","golden":"nine","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"}]},{"eval_id":"019e05f2-f42c-7018-ab71-30b51adf12e2","probe":"What is the name of the region located between the right and left lumbar regions?","golden":"Umbilical region","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"}]},{"eval_id":"019e05f3-f4bd-74db-9544-35cd14788275","probe":"What is the name of the region directly above the umbilical region?","golden":"Epigastric region","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"}]},{"eval_id":"019e05f4-56d1-7193-845a-2889286704f6","probe":"How many abdominal quadrants are shown in figure (b)?","golden":"four","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"}]},{"eval_id":"019e05f6-e2c6-7b53-b37c-1808bd28b0d4","probe":"What organ is shown as the example at the Organ level in the pyramid?","golden":"Bladder","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"}]},{"eval_id":"019e05f7-dd30-7195-830e-cd261e20c2b7","probe":"What organ system is shown as the example at the Organ system level?","golden":"Urinary tract system","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"}]},{"eval_id":"019e05f9-174d-779b-8451-840365bb3ab1","probe":"What type of muscle cell is shown at the Cellular level in the pyramid?","golden":"Smooth muscle cell","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"}]},{"eval_id":"019e05fa-5cd7-7bf5-ad75-0aa2f060da1e","probe":"What is the name of the plane shown at the bottom of the figure, near the body's feet?","golden":"Oblique plane","png_sha":"d0de1bb560e9b722942304e532a14882201f7692dbe44333b38e37a146f08834","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"}]},{"eval_id":"019e0a71-d77a-7463-8c88-e70ccbeb93a7","probe":"How many electrons are shown in the cloud of negative charge?","golden":"2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"}]},{"eval_id":"019e0a77-521b-7c1e-96e5-0fcfd2acccfb","probe":"How many positive charges are shown in the nucleus of the electron cloud model?","golden":"2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"}]},{"eval_id":"019e0a78-60c3-7ff1-a58d-36cf79d83532","probe":"What is the pH of blood?","golden":"7.4","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"}]},{"eval_id":"019e0a78-c1e6-7be1-b2ed-7370055ce7a4","probe":"What is the pH of baking soda?","golden":"9.5","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"}]},{"eval_id":"019e0a79-38e3-7203-9d9c-b65c2c843999","probe":"What is the pH of black coffee?","golden":"5","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e0a7f-36c1-76f1-9b7d-a75d3f8b57bc","probe":"What are the regions of the enzyme called where substrates bind?","golden":"Active sites","png_sha":"56f42b1466f0ba4fd23da4bdafef8224d214d10ff10aa671d80ddc4389ea94dd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"}]},{"eval_id":"019e0a7f-f372-7caa-bdd1-9371e7bc0c6a","probe":"How many chromosomes does the page say are inside the nucleus of each cell?","golden":"46","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"}]},{"eval_id":"019e0a80-2d48-78ae-9837-df877d92d50a","probe":"Approximately how many genes do humans have in their DNA according to this page?","golden":"22,000","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"}]},{"eval_id":"019e0a80-c197-7fce-a219-ddb90e59c15f","probe":"What color represents Guanine in the diagram?","golden":"Blue","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"}]},{"eval_id":"019e0a81-1a13-7011-bf33-0b2b8c97db32","probe":"What color represents Adenine in the diagram?","golden":"Red","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"}]},{"eval_id":"019e0a82-da2f-727f-896b-27e752c2b42b","probe":"What are the two types of fatty acids labeled in the phospholipid diagram?","golden":"Saturated fatty acid and unsaturated fatty acid","png_sha":"a2c418cbcdc6704d925ad4ffdd78dee38a58fc1ea68774d0094b65c486a66bf8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"}]},{"eval_id":"019e0a83-ca15-7698-adf8-be9e8fecc270","probe":"What is labeled as the area inside the cell in the large membrane illustration?","golden":"Intracellular","png_sha":"a2c418cbcdc6704d925ad4ffdd78dee38a58fc1ea68774d0094b65c486a66bf8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"}]},{"eval_id":"019e0a8c-68fb-7f92-a952-b3faa7d123a4","probe":"What is the chapter title shown in the header at the top of the page?","golden":"Cell Membrane","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"}]},{"eval_id":"019e0a91-1c2e-7311-b881-fc5c00ce52f9","probe":"What does the arrow at the bottom of the diagram represent?","golden":"Time","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"}]},{"eval_id":"019e0a91-e6fb-79fb-b85f-ccfa87b7f449","probe":"What is labeled above the lipid bilayer in the center of the diagram?","golden":"Extracellular fluid","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"}]},{"eval_id":"019e0a92-7404-7aab-b271-b5cbb06491b3","probe":"What is labeled below the lipid bilayer in the center of the diagram?","golden":"Cytoplasm","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"}]},{"eval_id":"019e0a94-7773-7d3d-b4db-4925da2a4c81","probe":"What are the three labels above the cell images in Figure 3.1.6?","golden":"Hypertonic, Isotonic, Hypotonic","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"}]},{"eval_id":"019e0a94-dfda-768c-897f-34618204bf19","probe":"What is labeled between the two beakers in Figure 3.1.5?","golden":"Semipermeable membrane","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"}]},{"eval_id":"019e0aa6-cdb4-70a0-951f-040144680d97","probe":"What is labeled in purple at the center of the diagram?","golden":"Crystalline core","png_sha":"29f66040d5b404ad4868b569f57abcbd771a080fa8fcc185a3187093b4d3defb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"}]},{"eval_id":"019e0ab1-a72f-70b0-9619-a8e2a81fee46","probe":"What are the four nitrogenous bases listed in the legend?","golden":"Adenine, Thymine, Guanine, Cytosine","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"}]},{"eval_id":"019e0ab3-3b2c-7cf7-9e5a-87076b99eb2f","probe":"What color is used to represent Guanine in the legend?","golden":"Blue","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"}]},{"eval_id":"019e0ab4-5e27-7fa0-bdb3-55833bf40f16","probe":"What type of bonds connect the two DNA strands together according to the diagram?","golden":"Hydrogen bonds","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"}]},{"eval_id":"019e0ac7-674b-7f8f-ac85-ce02731c302a","probe":"How many stages are shown in the diagram at the top of the page?","golden":"6","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"}]},{"eval_id":"019e0ac8-36ba-7365-9435-ec92bf202c05","probe":"According to figure 3.5.3, what is the first phase of mitosis?","golden":"Prophase","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"}]},{"eval_id":"019e0ac9-ab1a-7551-88fe-ba669d0ab987","probe":"What is the last stage shown in the cell division diagram (after telophase)?","golden":"Cytokinesis","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"}]},{"eval_id":"019e0ad3-52d5-7f4c-8d3d-591d2476cefd","probe":"What is at the very top of the stem cell differentiation diagram?","golden":"Totipotent embryonic stem cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"}]},{"eval_id":"019e0adb-d424-739a-88c3-a9c6837b69aa","probe":"What type of stem cell is at the top of the diagram?","golden":"Totipotent embryonic stem cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"}]},{"eval_id":"019e0ae7-f32b-7670-af77-ced5432c5f69","probe":"What specialized cell type is shown between 'Heart muscle' and 'Skin' in the bottom row?","golden":"Red blood cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"}]},{"eval_id":"019e0b0b-0842-7562-aaee-a34590209d11","probe":"What is the figure title for Figure 4.6.2?","golden":"Development of Cancer","png_sha":"c97dbfb9dac36762398856cdab61d5779eae44284b94b744c8e56704bbf954e8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"}]},{"eval_id":"019e0b18-8c5a-7124-bb30-6bd93445411f","probe":"What does the label point to in the middle diagram?","golden":"Cell division accelerates","png_sha":"c97dbfb9dac36762398856cdab61d5779eae44284b94b744c8e56704bbf954e8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"}]},{"eval_id":"019e0b35-2b57-7c4e-9af5-fa094b59bb2c","probe":"What cell type is shown in the bottom-right image of the diagram?","golden":"Pancreatic cell","png_sha":"7b24760285552c0a3e2beb4a713373cf7079657b1996b630c4cab49bb81d2a0c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"}]},{"eval_id":"019e0eaf-c1cd-797e-834b-863d872f236e","probe":"What cell type is shown in the bottom-left image of the diagram?","golden":"Lung cell","png_sha":"7b24760285552c0a3e2beb4a713373cf7079657b1996b630c4cab49bb81d2a0c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"}]},{"eval_id":"019e0eb0-b4d4-72a3-99bd-8214864274dd","probe":"Which long bone is shown as the example in the diagram?","golden":"Femur","png_sha":"649d7b93ee3bd97ec82fa0d6dc7eb1ef1d3a531661aaf8e5a64a2e776e7befdf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"}]},{"eval_id":"019e0eb5-35af-7967-8d48-00aa0aa1a645","probe":"According to table 11.4, what is the origin of the superior oblique?","golden":"Sphenoid bone","png_sha":"e52a483f3e3402fc6874a991f546b566e2a6a0e32ba17df2ef455c46bc8e0793","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"}]},{"eval_id":"019e0eb7-fc68-7c2e-ad2c-3675d09c8aa1","probe":"What color represents the appendicular skeleton in the diagram's key?","golden":"Purple","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"}]},{"eval_id":"019e0eb9-5156-79fe-85f7-13b631e40c4d","probe":"What is the bone labeled between the Tibia and the Tarsals on the lower leg?","golden":"Fibula","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"}]},{"eval_id":"019e0eb9-c545-743f-b1c1-6053776f3ffb","probe":"What bone is labeled directly below the Humerus on the arm?","golden":"Ulna","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"}]},{"eval_id":"019e0eba-022c-7bba-8967-31ab884feb4d","probe":"What is the bone labeled directly below the Femur in the diagram?","golden":"Patella","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"}]},{"eval_id":"019e0eba-8701-7de9-8ba9-578294d6b194","probe":"What is the bone labeled directly between the Clavicle and the Thoracic cage?","golden":"Scapula","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"}]},{"eval_id":"019e0ebb-0d43-793d-85f7-7b2ed1575cdf","probe":"What is the bone labeled directly below the Radius on the arm?","golden":"Carpals","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"}]},{"eval_id":"019e0ebd-9465-739b-8454-3efaee4d4310","probe":"What is the label directly below 'Rotator brevis' in the Deep spinal muscles diagram?","golden":"Rotator longus","png_sha":"8267a338f131676cd4f156eb0c4a18c6d48352ad7a386fd12707e7503673af3f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"}]},{"eval_id":"019e0ebf-4889-76bf-9d21-fdeaa9903ac1","probe":"On the left hand side of the left lateral view, what muscle is labeled directly above the Anterior scalene?","golden":"Medial scalene","png_sha":"8267a338f131676cd4f156eb0c4a18c6d48352ad7a386fd12707e7503673af3f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"}]},{"eval_id":"019e0ec1-bc36-7c2e-a816-0d61d873fe40","probe":"What file name is shown in the WebScope micrograph?","golden":"054 - Peripheral nerve_001.svs","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"}]},{"eval_id":"019e0ec6-5ccb-7a48-a454-ea039c311db0","probe":"In the leftmost (first) stage of figure (a), what two structures are labeled?","golden":"Nucleus and Axon","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"}]},{"eval_id":"019e0ec7-9679-765e-943c-61c133fe490f","probe":"Which structure label appears in the rightmost (third) stage of figure (a)?","golden":"Node of Ranvier","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"}]},{"eval_id":"019e0eca-119a-763f-ac56-f38e33c22003","probe":"What four carpal bones are labeled in the figure 8.2.5?","golden":"Hamate, Trapezoid, Trapezium, Capitate","png_sha":"306e13b6e12dfea3dcc83ac66671b7f4f26e03a8658a38703694470c4b84acff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"}]},{"eval_id":"019e0ecc-c17a-7df3-a1f4-407930ed7366","probe":"How many distinct structures are labeled with leader lines on this figure?","golden":"5","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e0ecd-0967-77f3-a1b2-140685a06b07","probe":"What structure is labeled at the very top of the cell?","golden":"Microvilli","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"}]},{"eval_id":"019e0ecd-62a5-7179-841c-8e4ba5c98a0a","probe":"What structure is labeled at the very bottom of the cell?","golden":"Nucleus","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"}]},{"eval_id":"019e0ece-41ab-74ba-b577-6e0aff6ee57c","probe":"What labeled structure appears between the Rough ER and the Nucleus?","golden":"Golgi apparatus","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"}]},{"eval_id":"019e0ece-aeb7-7000-b806-b1e7d144e6f6","probe":"What color is used to depict the Golgi apparatus in this figure?","golden":"orange","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"}]},{"eval_id":"019e0ed6-4075-7e2a-8d36-a54c01ef1f0a","probe":"According to the labels in the figure, which Roman numeral is assigned to the Olfactory nerve?","golden":"I","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"}]},{"eval_id":"019e0ed6-d0db-7047-a35c-28a5f0394d4e","probe":"How many cranial nerves are labeled in this figure?","golden":"12","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"}]},{"eval_id":"019e0ed7-29c1-7353-a0d0-78dc86f5bf0d","probe":"Which cranial nerve is labeled with the Roman numeral X?","golden":"Vagus nerve","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"}]},{"eval_id":"019e0ed7-a580-70c5-9af2-82e1e6d3b27c","probe":"Which cranial nerve is labeled directly above the Trochlear nerve on the left side of the figure?","golden":"Oculomotor nerve","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"}]},{"eval_id":"019e0ed8-e384-740f-8339-b731e7477bd0","probe":"Which Roman numeral is assigned to the Trigeminal nerve?","golden":"V","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"}]},{"eval_id":"019e0edf-b3c8-7227-995d-59d8e7337a13","probe":"What is the membrane potential value at the dashed horizontal line labeled \"Threshold\"?","golden":"-55 mV","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"}]},{"eval_id":"019e0ee0-04e8-7f4f-a3d3-f732f8ce4367","probe":"What does the x-axis represent?","golden":"Time","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"}]},{"eval_id":"019e0ee2-00eb-788b-982a-17e9bbe92888","probe":"How many separate cross-section illustrations are shown in Figure 14.1.1","golden":"3","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"}]},{"eval_id":"019e0ee4-1b7c-773f-963c-fc9c8846cdc2","probe":"In the rightmost (third) illustration of Figure 14.1.1, what label appears at the far right?","golden":"Ectoderm","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"}]},{"eval_id":"019e0ee5-7413-77ac-928e-9349a0add2e3","probe":"In the far-left illustration of Figure 14.1.1, what word is labeled at the end of the curved arrow?","golden":"Convergence","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"}]},{"eval_id":"019e0ee7-d44b-7f7f-9dde-44db50c5a6d7","probe":"In panel (a), what label is shown at the top-left of the panel?","golden":"Resting muscle","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"}]},{"eval_id":"019e0ee8-0c80-7766-bb63-e01a6477af62","probe":"In panel (a), what label is shown at the top-right of the panel?","golden":"Active muscle","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"}]},{"eval_id":"019e0ee8-b795-7df0-985e-b6a23bc84e11","probe":"In panel (b), what process is shown at the top-right when oxygen is present?","golden":"Aerobic respiration","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"}]},{"eval_id":"019e0ee9-027b-7c34-9c19-e3a9f92ddc36","probe":"In panel (b), what is produced when there is no oxygen?","golden":"Lactic acid","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"}]},{"eval_id":"019e0ee9-9d8a-74f4-a4d4-fdae97459d0d","probe":"In panel (c), what three substances flow INTO the cellular respiration mitochondria?","golden":"Blood glucose, Pyruvic acid, Fatty acids","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"}]},{"eval_id":"019e0eee-1192-75e7-bc00-9eba77492379","probe":"In Figure 17.5.2, what does step 1 say?","golden":"Blood calcium concentration drops","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"}]},{"eval_id":"019e0eee-6b0f-7623-9bf9-f65dcda769bd","probe":"In Figure 17.5.2, what does step 4 say?","golden":"Blood calcium levels increase","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"}]},{"eval_id":"019e0ef0-10bf-71af-9ca6-cd2d668f1d1c","probe":"In Figure 17.5.2, what does step 6 describe the effects of?","golden":"calcitonin on bone","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"}]},{"eval_id":"019e0ef1-0b05-7277-bad0-8b16372f30ef","probe":"In Figure 17.5.2, what is the title of item 3b?","golden":"Effects of PTH on kidneys","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"}]}]},{"summary":{"model":"claude_sonnet_4_6","name":"Claude Sonnet 4.6","total_evals":550,"total_cells":16500,"l2_cells":15197,"l3_cells":1097,"l4_cells":206,"acceptable":98.75,"runs":30,"partial":false,"l2_evals":497,"l3_evals":43,"l4_evals":10},"evals":[{"eval_id":"019dfb22-9390-7dca-91a4-198eb5ec30b4","probe":"What is the amortized cost net of ACL for Baa rated securities as of December 31, 2022?","golden":"$81,280 million","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"81,280"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"81,280"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"81,280"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"81,280"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"81,280"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"}]},{"eval_id":"019e0081-be2e-71be-9017-964db6e9e08a","probe":"What is the maximum value shown on the map's mile scale bar?","golden":"45 Miles","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"40 Miles"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":24,"verdict":4,"source":"precedent","note":"wrong value","answer":"40 Miles"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"40"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"40"}]},{"eval_id":"019e00ac-faaf-7e38-b571-92ff92b76932","probe":"Garcia of California voted in which column?","golden":"NAYS","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong category","answer":"Yeas"},{"run_index":1,"verdict":4,"source":"human","note":"wrong category","answer":"Yeas"},{"run_index":2,"verdict":4,"source":"human","note":"wrong category","answer":"Yeas"},{"run_index":3,"verdict":4,"source":"human","note":"wrong category","answer":"Yeas"},{"run_index":4,"verdict":4,"source":"human","note":"wrong category","answer":"Yeas"},{"run_index":5,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":6,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":7,"verdict":4,"source":"precedent","note":"wrong category","answer":"Yeas"},{"run_index":8,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":9,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":10,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":11,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":12,"verdict":4,"source":"precedent","note":"wrong category","answer":"Yeas"},{"run_index":13,"verdict":4,"source":"precedent","note":"wrong category","answer":"Yeas"},{"run_index":14,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":15,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":16,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":17,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":18,"verdict":4,"source":"precedent","note":"wrong category","answer":"Yeas"},{"run_index":19,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":20,"verdict":4,"source":"precedent","note":"wrong category","answer":"Yeas"},{"run_index":21,"verdict":4,"source":"precedent","note":"wrong category","answer":"Yeas"},{"run_index":22,"verdict":4,"source":"precedent","note":"wrong category","answer":"Yeas"},{"run_index":23,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":24,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":25,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":26,"verdict":4,"source":"precedent","note":"wrong category","answer":"Yeas"},{"run_index":27,"verdict":4,"source":"precedent","note":"wrong category","answer":"Yeas"},{"run_index":28,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":29,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"}]},{"eval_id":"019e0529-025b-7daa-a5e9-a453809b33ba","probe":"How many sponsors were added to H. Res. 23?","golden":"15","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"13"},{"run_index":1,"verdict":4,"source":"human","note":"wrong count","answer":"13"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"13"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"13"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"13"},{"run_index":5,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":6,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":7,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":8,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":9,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":10,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":11,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":12,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":13,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":14,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":15,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":16,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":17,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":18,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":19,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":20,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":21,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":22,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":23,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":24,"verdict":4,"source":"precedent","note":"wrong count","answer":"14"},{"run_index":25,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":26,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":27,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":28,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":29,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"}]},{"eval_id":"019e0529-ab42-7f49-b945-e7fa7946e4e8","probe":"Who was added as a sponsor to H.R. 493?","golden":"Ms. DelBene","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. Austin Scott of Georgia"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. Austin Scott of Georgia"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. Austin Scott of Georgia"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Austin Scott of Georgia"}]},{"eval_id":"019de200-d4eb-7ccd-933d-0af15a613cf0","probe":"What is the Alteration Threshold dollar amount?","golden":"$200,000.00","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$300,000.00"}]},{"eval_id":"019dfafb-dcbb-70a3-96b4-fcb14e3ee61c","probe":"What was the cost of revenues for 2023?","golden":"$133,332 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"}]},{"eval_id":"019dfb20-e27a-7c39-b2f6-4f9d7929ea4e","probe":"What is the estimated fair value of total fixed maturity securities AFS as of December 31, 2022?","golden":"$276,780 million","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"276,780"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"276,780"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"276,780"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"276,780"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"}]},{"eval_id":"019e05ad-fd6c-7734-88ed-1ec50c394ff9","probe":"How many conditions are listed under \"Strong or Consistent Association With Progression to Severe COVID-19\"?","golden":"8","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"9"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"9"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":5,"verdict":4,"source":"human","note":"wrong count","answer":"9"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":17,"verdict":4,"source":"human","note":"wrong count","answer":"9"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":25,"verdict":4,"source":"human","note":"wrong count","answer":"9"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"}]},{"eval_id":"019e0ee8-0c80-7766-bb63-e01a6477af62","probe":"In panel (a), what label is shown at the top-right of the panel?","golden":"Active muscle","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":1,"verdict":4,"source":"human","note":"wrong label","answer":"Creatine"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"}]},{"eval_id":"019de200-d496-74b2-a2cc-5c7a6982836d","probe":"What is the Tenant Notice Address suite number?","golden":"Suite 900","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"}]},{"eval_id":"019de200-d505-7a87-bf67-4ac7fc6b2fd3","probe":"How many days before policy expiration must original copies of policies be delivered to Landlord?","golden":"fifteen (15) days","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"15 days"},{"run_index":1,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"15 days"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"15 days"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"15 days"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"15 days"},{"run_index":5,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":6,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":7,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":8,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":9,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":10,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":11,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":12,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":13,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":14,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":15,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":16,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":17,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":18,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":19,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":20,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":21,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":22,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":23,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":24,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":25,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":26,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":27,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":28,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":29,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"}]},{"eval_id":"019de200-d50e-7050-b563-d96d07356800","probe":"How many times per day must the exterior of the building be inspected and maintained?","golden":"four times per day","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4"},{"run_index":1,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4"},{"run_index":5,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":6,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":7,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":8,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":9,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":10,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":11,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":12,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":13,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":14,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":15,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":16,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":17,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":18,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":19,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":20,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":21,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":22,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":23,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":24,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":25,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":26,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":27,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":28,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":29,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"}]},{"eval_id":"019de200-d515-7626-bd30-2e0c3b0c3b7f","probe":"Within how many Business Days must Borrower pay any excess if it results from a reserve against the Borrowing Base?","golden":"five (5) Business Days","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019de200-d523-7d03-9cf0-aa0eb615e454","probe":"Within how many calendar days following lease termination must Lessor conduct and deliver the Phase I environmental assessment under section 11.4?","golden":"fifteen (15) calendar days","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"}]},{"eval_id":"019de200-d525-7710-85f5-fc41b54afbb0","probe":"Within how many calendar days must Lessee deliver a signed counterpart of the sublease agreement to Lessor after its execution?","golden":"five (5) calendar days","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019dfaef-4f26-7d15-9caf-4928cafc4f5e","probe":"What is the exhibit number shown at the top right of this page?","golden":"Exhibit 23.1","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"}]},{"eval_id":"019dfb3f-d06a-7547-a4b6-8a6e4c150c61","probe":"What is the suite number of the office address listed at the bottom of the letter?","golden":"Suite 1850","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"}]},{"eval_id":"019e0005-d4aa-7f1f-8391-f99f6caf3697","probe":"How many City Council Members are from Brooklyn?","golden":"16 Members","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"}]},{"eval_id":"019e0006-0655-7fe4-88c4-d697fbcb759a","probe":"How many Council Members does Queens have?","golden":"14 Members","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"}]},{"eval_id":"019e003d-d1bc-7fb0-a78b-4b79600f8252","probe":"Who is the Custodian of Funds?","golden":"Brad Lander, Comptroller of the City of New York","png_sha":"89c77daf9c6f881f0116f445cbf736cffc12698b60a93b437699a1a075b00138","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":1,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":2,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":3,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":4,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":5,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":6,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":7,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":8,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":9,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":10,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":11,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":12,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":13,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":14,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":15,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":16,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":17,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":18,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":19,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":20,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":21,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":22,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":23,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":24,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":25,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":26,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":27,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":28,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":29,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"}]},{"eval_id":"019e0085-cd0d-7043-93eb-a33714bb645a","probe":"What GASB Statement number did the Council adopt in fiscal year 2024?","golden":"No. 96","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"}]},{"eval_id":"019e00a7-39d7-723b-9490-eca9ac160ad7","probe":"What time did the House reconvene after recess?","golden":"1:30 p.m.","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":1,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":2,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":3,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":4,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":5,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":6,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":7,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":8,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":9,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":10,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":11,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":12,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":13,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":14,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":15,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":16,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":17,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":18,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":19,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":20,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":21,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":22,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":23,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":24,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":25,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":26,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":27,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":28,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":29,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."}]},{"eval_id":"019e00ad-aa7b-733c-8e2b-33b7f30d7cfc","probe":"Did Senator Whittaker appear on this vote?","golden":"No, Whittaker is not listed on this page","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":5,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":6,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":7,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":8,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":9,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":10,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":11,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":12,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":13,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":14,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":15,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":16,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":17,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":18,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":19,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":20,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":21,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":22,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":23,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":24,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":25,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":26,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":27,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":28,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":29,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"}]},{"eval_id":"019e00af-5886-7c0c-acb0-3467635835d6","probe":"What time did the recorded vote take place (the \u25a1 time stamp before the McGOVERN demand)?","golden":"1:56 PM (1356)","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"}]},{"eval_id":"019e00af-a493-76fe-9fc1-0e6baa42ab53","probe":"What time did the House return from recess (the \u25a1 time stamp before \"AFTER RECESS\")?","golden":"1:30 PM (1330)","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":1,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":2,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":3,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":4,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":5,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":6,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":7,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":8,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":9,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":10,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":11,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":12,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":13,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":14,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":15,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":16,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":17,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":18,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":19,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":20,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":21,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":22,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":23,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":24,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":25,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":26,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":27,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":28,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":29,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."}]},{"eval_id":"019e00b0-60e7-7eb0-ace3-4de6646279c2","probe":"Which members changed their vote from \"yea\" to \"nay\"?","golden":"Ms. Ross, Mrs. Foushee, Mr. Raskin, and Mr. Krishnamoorthi","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":1,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":2,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":3,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":4,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":5,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":6,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":7,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":8,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":9,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":10,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":11,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":12,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":13,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":14,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":15,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":16,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":17,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":18,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":19,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":20,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":21,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":22,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":23,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":24,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":25,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":26,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":27,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":28,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":29,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"}]},{"eval_id":"019e00b5-3554-76cc-805e-ff8228bfefae","probe":"What was the rollcall vote number for the vote on Amendment No. 8?","golden":"Rollcall Vote No. 6 Leg.","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"}]},{"eval_id":"019e00b6-0ba2-731c-a9ed-436b1a7ef320","probe":"What was the rollcall vote number for the vote on S. 5?","golden":"Rollcall Vote No. 7 Leg.","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"}]},{"eval_id":"019e051b-f048-7557-907e-87bf1f5319e0","probe":"What was the rollcall vote number for the Driscoll nomination?","golden":"Rollcall Vote No. 90 Ex.","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"}]},{"eval_id":"019e054b-b654-74aa-b2b0-ad19e229a916","probe":"What is the preferred alternative immunomodulator listed for hospitalized patients requiring HFNC oxygen or NIV?","golden":"IV tocilizumab (Blla)","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"}]},{"eval_id":"019e05ac-b930-79c4-93f6-be96e504477e","probe":"Within how many months of a recent SARS-CoV-2 infection may substantial immunity be conferred, according to footnote b?","golden":"3-6 months","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"}]},{"eval_id":"019e05b5-b5f0-7a24-b00b-652882db4074","probe":"What plateau pressure does the Panel recommend targeting?","golden":"<30 cm H2O","png_sha":"f2687af1be946044a236b7f11f8cf6f728ef1c4e9e442378d2a6ad846b6a54e4","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":2,"verdict":3,"source":"human","note":"answer expanded","answer":"Less than 30 cm H\u2082O"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":4,"verdict":3,"source":"human","note":"answer expanded","answer":"Less than 30 cm H\u2082O"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":11,"verdict":3,"source":"human","note":"answer expanded","answer":"Less than 30 cm H\u2082O"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":15,"verdict":3,"source":"human","note":"answer expanded","answer":"Less than 30 cm H\u2082O"},{"run_index":16,"verdict":3,"source":"human","note":"answer expanded","answer":"Less than 30 cm H\u2082O"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":21,"verdict":3,"source":"human","note":"answer expanded","answer":"Less than 30 cm H\u2082O"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":23,"verdict":3,"source":"human","note":"answer expanded","answer":"Less than 30 cm H\u2082O"},{"run_index":24,"verdict":3,"source":"human","note":"answer expanded","answer":"Less than 30 cm H\u2082O"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"}]},{"eval_id":"019e0a77-09dc-7990-a971-9e556b040d8c","probe":"What symbol is used to label the electron in the planetary model?","golden":"e\u2212","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"}]},{"eval_id":"019e0a9d-62f1-726d-9b24-bbeb2b85b199","probe":"According to the caption of Figure 3.1.5, which side of the membrane (left or right) shows the hypertonic solution?","golden":"the right side","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"Right"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"Right"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"Right"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"Right"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"Right"},{"run_index":5,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":6,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":7,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":8,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":9,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":10,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":11,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":12,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":13,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":14,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":15,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":16,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":17,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":18,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":19,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":20,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":21,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":22,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":23,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":24,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":25,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":26,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":27,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":28,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"},{"run_index":29,"verdict":3,"source":"precedent","note":"article handling","answer":"Right"}]},{"eval_id":"019e0a9e-aa0f-7a55-89e3-a0cd7f73e21f","probe":"What chemical formula is shown next to each red blood cell in the bottom row of Figure 3.1.6?","golden":"H2O","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"}]},{"eval_id":"019e0ad4-4005-7307-aae9-78e3049f1a65","probe":"What are the three lines that pluripotent embryonic stem cells differentiate into?","golden":"Endoderm, Mesoderm, and Ectoderm","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":5,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":6,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":7,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":8,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":9,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":10,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":11,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":12,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":13,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":14,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":15,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":16,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":17,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":18,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":19,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":20,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":21,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":22,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":23,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":24,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":25,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":26,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":27,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":28,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":29,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"}]},{"eval_id":"019e0ed2-1e72-7fe1-94ee-e4dcffb88ace","probe":"In figure (a), what body part is gripping the pencil?","golden":"a hand","png_sha":"294a4958d5ff0d4328b9ea9e75f13bb4f7ef1d09ee59316db09945f970fa281f","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"Hand"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"Hand"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"Hand"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"Hand"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"Hand"},{"run_index":5,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":6,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":7,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":8,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":9,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":10,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":11,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":12,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":13,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":14,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":15,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":16,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":17,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":18,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":19,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":20,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":21,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":22,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":23,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":24,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":25,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":26,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":27,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":28,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":29,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"}]},{"eval_id":"019e0ede-f3cd-7412-8c25-2e079510e6e7","probe":"What is the unit shown on the y-axis label?","golden":"mV (millivolts)","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"}]},{"eval_id":"019e0ee9-9d8a-74f4-a4d4-fdae97459d0d","probe":"In panel (c), what three substances flow INTO the cellular respiration mitochondria?","golden":"Blood glucose, Pyruvic acid, Fatty acids","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":1,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":2,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":3,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":4,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":5,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":6,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":7,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":8,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":9,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":10,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":11,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":12,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":13,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":14,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":15,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":16,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":17,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":18,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":19,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":20,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":21,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":22,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":23,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":24,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":25,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":26,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":27,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":28,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":29,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"}]},{"eval_id":"019e0eea-ac39-7b97-941e-8c1e0a744ae3","probe":"In panel (c), what additional input enters the mitochondria from above (with a downward arrow)?","golden":"O\u2082 (oxygen)","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"}]},{"eval_id":"019de200-d508-7af1-93e1-8436c404657e","probe":"How many business days in advance must Tenant provide the Notice of Permitted Transfer?","golden":"10 Business Days","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"}]},{"eval_id":"019de200-d518-778a-9421-02c7d2e3a05a","probe":"What is the section number for 'Time is of the Essence'?","golden":"Section 1.4","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"}]},{"eval_id":"019de740-e7d8-75d0-835d-3a79745c66cc","probe":"How many consecutive Business Days after Landlord's receipt of the Untenantability Notice are required (in non-Force Majeure cases)?","golden":"five (5)","png_sha":"658d8ecfa29b1c0cf9870b2d1c622a5cff7347859e7674b418cc4660be4eb7b9","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five (5)"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019de778-2487-7ceb-942f-bbc9cce683b5","probe":"What is the public law number?","golden":"118-109","png_sha":"a0300e50b30b31b24996ac843a50187dca0d8e81f6c026161ae3e07159e9815a","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"118\u2013109"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"118\u2013109"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"118\u2013109"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"}]},{"eval_id":"019e05e9-158a-7e0b-a377-74df9d26138b","probe":"How many abdominal regions are shown in figure (a)?","golden":"nine","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":1,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":5,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":6,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":7,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":8,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":9,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":10,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":11,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":14,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":15,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":16,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":17,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":20,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":23,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":24,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":28,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"}]},{"eval_id":"019e05f4-56d1-7193-845a-2889286704f6","probe":"How many abdominal quadrants are shown in figure (b)?","golden":"four","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":7,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":8,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":9,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":10,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":12,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":17,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":20,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":21,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":24,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":27,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":29,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"}]},{"eval_id":"019e0a6f-0c3e-7520-884b-307d309c1b4b","probe":"What percentage of the human body is oxygen?","golden":"65.0%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"65.0%"}]},{"eval_id":"019e0a70-8117-7662-8777-c2511bc6f2ee","probe":"What percentage of the human body is phosphorus?","golden":"1.0%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"}]},{"eval_id":"019e0a71-574c-7f62-97db-97525ad2820e","probe":"What is the figure number for the two models of atomic structure?","golden":"Figure 2.1.2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"}]},{"eval_id":"019e0a76-b33e-7648-8be4-ced32e601bf5","probe":"What element is shown in the planetary model?","golden":"Helium (He)","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"}]},{"eval_id":"019e0ac6-e7e3-7800-ac52-eee064e4e8b7","probe":"What is the scale bar length shown in the microscope images?","golden":"5 \u03bcm","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"}]},{"eval_id":"019e0edf-b3c8-7227-995d-59d8e7337a13","probe":"What is the membrane potential value at the dashed horizontal line labeled \"Threshold\"?","golden":"-55 mV","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":7,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":8,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":12,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":13,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":14,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":15,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":16,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately -55 mV"},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":22,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":23,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":24,"verdict":3,"source":"human","note":"glyph variant","answer":"\u201355 mV"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately -55 mV"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately -55 mV"},{"run_index":27,"verdict":3,"source":"human","note":"answer expanded","answer":"approximately \u201355 mV"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately -55 mV"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately -55 mV"}]},{"eval_id":"019de200-d48b-7a0c-9e79-d846c27a96b5","probe":"What page does Article XI Security Deposit start on?","golden":"50","png_sha":"625ba89847b64383ae07efde4a0b7374c88fd2b6dcff552df6812dad32d03160","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"}]},{"eval_id":"019de200-d48c-70ff-b28a-a9c240e3486b","probe":"Who is the landlord named on this office lease?","golden":"Lanham Office 2015 LLC","png_sha":"625ba89847b64383ae07efde4a0b7374c88fd2b6dcff552df6812dad32d03160","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lanham Office 2015 LLC"}]},{"eval_id":"019de200-d48d-703c-b522-b34424519003","probe":"What is Exhibit L?","golden":"Competitor List","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"}]},{"eval_id":"019de200-d48e-767a-b928-9b2d12086653","probe":"What is Exhibit H?","golden":"Roof Access Agreement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"}]},{"eval_id":"019de200-d48f-7596-abf5-cacd23054c4d","probe":"What is Exhibit J?","golden":"Parking Easement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"}]},{"eval_id":"019de200-d490-71ff-a39d-ee962a11796e","probe":"What is Exhibit D?","golden":"Certificate Affirming the Must Take Commencement Date","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"}]},{"eval_id":"019de200-d491-71d6-875d-4fa564623978","probe":"What is Exhibit B?","golden":"Work Agreement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"}]},{"eval_id":"019de200-d492-726b-87fc-5718790d5ebd","probe":"What is Exhibit E?","golden":"Measurement Schedule","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"}]},{"eval_id":"019de200-d493-74c3-af46-0469929cc88d","probe":"What is the Tenant Notice Address?","golden":"8201 Corporate Drive, Suite 900, Landover, MD 20785","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full business operations commenced), then the Premises, Attention: Chief Financial Officer, with a copy to: General Counsel."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (initially), then the Premises, Attention: Chief Financial Officer, with a copy to: General Counsel."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full business operations commence), thereafter the Premises, Attention: Chief Financial Officer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full business operations commence), then the Premises, Attention: Chief Financial Officer, with a copy to: General Counsel."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full business operations commence), then the Premises, Attention: Chief Financial Officer, with a copy to: General Counsel."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (initially), then the Premises, Attention: Chief Financial Officer, with a copy to: General Counsel."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785"}]},{"eval_id":"019de200-d494-73d8-930e-be33d26373fa","probe":"What section is referenced for the definition of 'Tax Benefits'?","golden":"Section 5.6","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"}]},{"eval_id":"019de200-d495-7bf0-9c87-96d57c098e71","probe":"What section is referenced for the definition of 'Threshold Successors'?","golden":"Section 10.1","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"}]},{"eval_id":"019de200-d497-758c-9ad2-fceee7efd1fa","probe":"What section is referenced for the definition of 'Tenant's Plans'?","golden":"Section 9.4(a)","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"}]},{"eval_id":"019de200-d498-741d-b3e0-3374c9b02dfc","probe":"What is the title of section H?","golden":"Tenant Modular Furniture","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant Modular Furniture"}]},{"eval_id":"019de200-d499-74c0-a9b3-74b464fcf74b","probe":"What is the color name listed for the carpet base?","golden":"503 Ginger","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"}]},{"eval_id":"019de200-d49a-7b22-8b95-3fe120b21efc","probe":"What is the section number for the CARPET section?","golden":"09680","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"}]},{"eval_id":"019de200-d49b-76ae-aecb-69e6ba967a73","probe":"What is the section number for the PAINTING section?","golden":"09900","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"}]},{"eval_id":"019de200-d49c-75ca-963f-0649d0c70719","probe":"What is the section number for ACOUSTICAL CEILING?","golden":"09510","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"}]},{"eval_id":"019de200-d49d-7cee-91a2-4ed07626e90a","probe":"What is the name of the company shown in the schedule heading on this page?","golden":"Acadia Realty Trust","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"}]},{"eval_id":"019de200-d49e-7120-8c57-be2e37f1a894","probe":"What is the page number shown at the bottom of the upper section of this page?","golden":"166","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"}]},{"eval_id":"019de200-d49f-72ce-9b9d-97ba16d5640c","probe":"What is the depreciation period (useful life in years) listed in the rightmost column for every property on this page?","golden":"40 years","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"}]},{"eval_id":"019de200-d4a0-7403-856e-aa22d2bdae81","probe":"What is the name of the company shown at the top of the page?","golden":"Acceleron Pharma Inc.","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."}]},{"eval_id":"019de200-d4a1-7f82-aa55-38eac3b9b487","probe":"What is the total deferred tax assets for 2017 (in thousands)?","golden":"145,657","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"}]},{"eval_id":"019de200-d4a2-7a39-91ad-766fdf7c2010","probe":"What is the page number shown at the bottom center of the page?","golden":"F-29","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"}]},{"eval_id":"019de200-d4a3-7518-9715-cc1bb9edb084","probe":"What is the deferred revenue amount for 2016 (in thousands)?","golden":"1,666","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"}]},{"eval_id":"019de200-d4a4-7cca-a0e9-a3ce81d8b684","probe":"What is the federal income tax expense at the statutory rate for 2015?","golden":"34.0%","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"}]},{"eval_id":"019de200-d4a5-753e-87a5-2c51cb711be4","probe":"What is the Research and development credits amount for 2017 (in thousands)?","golden":"12,548","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"}]},{"eval_id":"019de200-d4a6-72d4-b715-3cd7f42e4f66","probe":"What is the State income tax, net of federal benefit percentage for 2016?","golden":"5.9%","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"}]},{"eval_id":"019de200-d4a7-74af-afa8-d3ad189499cc","probe":"What is the deposit amount mentioned in this document?","golden":"$500,000.00","png_sha":"5a5e3841491b2b356eb9b963e45419183ebf6ffae298e69a6f9dd5488bc23e1c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"}]},{"eval_id":"019de200-d4a8-7bdc-bc00-d50a60d60dcc","probe":"What is the title of section 16?","golden":"Mutual Waiver of Subrogation Rights","png_sha":"674a83793665d045c76513a816f7fc9099c52baccd94af7ee817a5f89cdc81d5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"}]},{"eval_id":"019de200-d4a9-7107-917d-4d1e160c26b3","probe":"What is the anticipated commencement date?","golden":"March 1, 2016","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"}]},{"eval_id":"019de200-d4aa-7225-85f5-76e6b1382af9","probe":"What is the premises address?","golden":"2665 North First Street, Suite 300, San Jose, California 95134","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"}]},{"eval_id":"019de200-d4ab-727c-ae0c-07bdc5f94836","probe":"What is the tenant's trade name?","golden":"8x8, Inc.","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."}]},{"eval_id":"019de200-d4ac-742d-b65a-74bd92f2893d","probe":"What is the name of the broker listed in Section 31?","golden":"Cresa Global, Inc.","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."}]},{"eval_id":"019de200-d4ad-71b2-aae9-616c2d5fdb91","probe":"What is the title of Section 33?","golden":"Holding Over","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"}]},{"eval_id":"019de200-d4ae-7bb5-8e56-dfba0d289a6a","probe":"What is the title of Section 38?","golden":"Miscellaneous","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"}]},{"eval_id":"019de200-d4af-7ae9-9bf2-f9ad2d8f5ea5","probe":"What is the title of Section 32?","golden":"Estoppel Certificate","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"}]},{"eval_id":"019de200-d4b0-7068-9693-c265751b0823","probe":"What is the title of Section 34?","golden":"Assignment and Subletting","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"}]},{"eval_id":"019de200-d4b1-72c3-a2c1-2ee5369782dd","probe":"What is the title of Section 31?","golden":"Broker's Commissions","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"}]},{"eval_id":"019de200-d4b2-7946-80ee-a29424252d23","probe":"What is the title of section 14.3?","golden":"Transfer Premium","png_sha":"cde4659cf5512e2c7b127af66eb4bab815dcc533bb04fce540d6d56b21cbb6cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"}]},{"eval_id":"019de200-d4b3-7330-8b3a-3010528a30fa","probe":"What is the title of section 14.5?","golden":"Effect of Transfer","png_sha":"cde4659cf5512e2c7b127af66eb4bab815dcc533bb04fce540d6d56b21cbb6cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"}]},{"eval_id":"019de200-d4b4-702e-932f-bb5b6dbb2b20","probe":"What is the title of Article XXIX?","golden":"Expansion Rights","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"}]},{"eval_id":"019de200-d4b5-709e-9897-f8440e2a964f","probe":"What is the title of Article XXX?","golden":"METROPLEX II ASSUMPTION","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex II Assumption"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex II Assumption"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex II Assumption"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex II Assumption"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex II Assumption"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex II Assumption"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex II Assumption"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"}]},{"eval_id":"019de200-d4b6-73e9-aa56-a2eb7119541a","probe":"What is the title of Section 29.1?","golden":"Right of First Refusal","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"}]},{"eval_id":"019de200-d4b7-7604-b550-db1d11ebef12","probe":"What is the title of Section 28.2?","golden":"Additional Amenities","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"}]},{"eval_id":"019de200-d4b8-7164-91b2-3ec03d9f397f","probe":"What is the title of section 12?","golden":"Severance Payments","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"}]},{"eval_id":"019de200-d4b9-723f-8a38-4f373e93bffa","probe":"What is the title of section 13?","golden":"Certain Covenants of the Executive","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"}]},{"eval_id":"019de200-d4ba-7ebb-acf4-de78451b07c1","probe":"How many miles is mentioned for relocation of the Executive's principal place of employment?","golden":"25 miles","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"}]},{"eval_id":"019de200-d4bb-7ca6-ada6-5158e0ca9947","probe":"What is the item number for the Foreperson/Day Porter Executive dress shirt?","golden":"#828","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"}]},{"eval_id":"019de200-d4bc-76fc-9589-06797f38e895","probe":"What is the title of section E?","golden":"UNIFORMS","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"}]},{"eval_id":"019de200-d4bd-7e20-a10a-47c622032b52","probe":"What is the item number for the women's Pleated Dress Pants?","golden":"#596","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"}]},{"eval_id":"019de200-d4be-7e4d-b5ce-bf5d0d9e3745","probe":"What is the title of section J?","golden":"LIGHTING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. LIGHTING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"}]},{"eval_id":"019de200-d4bf-7a42-91f9-d00fe759f635","probe":"What is the title of section H?","golden":"SECURITY AND INCIDENT REPORTING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"}]},{"eval_id":"019de200-d4c0-7843-8047-cc09e991e12b","probe":"What is the title of section K?","golden":"GREEN CLEANING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green Cleaning"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green Cleaning"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green Cleaning"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green Cleaning"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green Cleaning"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green Cleaning"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green Cleaning"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green Cleaning"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"}]},{"eval_id":"019de200-d4c1-76bf-b140-f4b73e70f7ed","probe":"What is the maximum sound level (in dBA) allowed for vacuum cleaners?","golden":"70dBA","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"}]},{"eval_id":"019de200-d4c2-7ad3-88a8-ed0b24b345b7","probe":"What is the item number for the men's Foreperson/Day Porter Pleated dress pants?","golden":"#865","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"}]},{"eval_id":"019de200-d4c3-7771-b087-cb7f248214a4","probe":"What is the item number listed for the women's Long Sleeve Dress Blouse?","golden":"#528","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"}]},{"eval_id":"019de200-d4c4-736b-b432-833199724c46","probe":"What is the title of section 24.0?","golden":"HOLDOVER","png_sha":"214b816ecbf747322726d54a0cb92edd6d184be6a6e04656e532d637c65eda11","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holdover"}]},{"eval_id":"019de200-d4c5-7b98-9a5a-c76d5fb5ae1e","probe":"What is the title of section 5.2?","golden":"Operating Expenses; Consumable Expenses and Base Building Expenses","png_sha":"3343506981bd41f08b63b8df40f8ba763e2bc1566a850d0903f24b1c5782cf77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."}]},{"eval_id":"019de200-d4c6-7729-866a-8ac3402457fb","probe":"What is the title of Article XIV?","golden":"Assignment and Subletting","png_sha":"d8fa233fb12db1beef1e4088d39215700d5884c2d4cb968b6985c6febde8a2ca","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"}]},{"eval_id":"019de200-d4c7-7305-82b7-76d4d75e7f9d","probe":"What is the title of Article XIII?","golden":"Condemnation","png_sha":"d8fa233fb12db1beef1e4088d39215700d5884c2d4cb968b6985c6febde8a2ca","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"}]},{"eval_id":"019de200-d4c8-787c-9ed4-e33640efb435","probe":"What is the title of Article 28?","golden":"Confidentiality","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"}]},{"eval_id":"019de200-d4c9-7b7f-9e32-c47d4f1c0b0e","probe":"What is the title of Exhibit D?","golden":"Form of Deed","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"}]},{"eval_id":"019de200-d4ca-7805-9cc9-6e26cd367bbc","probe":"What is the title of Article 25?","golden":"Waiver of Jury Trial","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"}]},{"eval_id":"019de200-d4cb-70dc-a225-ac7807b5a70c","probe":"What is the title of Article 33?","golden":"Costs and Attorneys' Fees","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"}]},{"eval_id":"019de200-d4cc-7013-9323-c4a463e49255","probe":"What is the Lessor's telephone number listed in the notices section?","golden":"(81) 8358.7978","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"}]},{"eval_id":"019de200-d4cd-7c1a-a4b1-fd5dc2875413","probe":"What is the title of section 24.4?","golden":"Captions","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"}]},{"eval_id":"019de200-d4ce-73b9-b787-b0f7568e7018","probe":"What is the Lessee's telephone number listed in the notices section?","golden":"(81) 8158.8800","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"}]},{"eval_id":"019de200-d4cf-7e95-8f4b-cca6ed5396ce","probe":"What is the title of section 24.5?","golden":"Severability","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"}]},{"eval_id":"019de200-d4d0-7008-bd98-2d410f1fb7fa","probe":"What is the name of the person to contact for the Lessor in the notices section?","golden":"Mr. Juan Carlos Gonzalez Quezada","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"}]},{"eval_id":"019de200-d4d1-7e39-92cb-dc82b006e040","probe":"What is the title of section 24.1?","golden":"Brokers","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"}]},{"eval_id":"019de200-d4d2-7ff3-ae3f-b7ce26ebedc4","probe":"What is the title of section 22.3?","golden":"Labor","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"}]},{"eval_id":"019de200-d4d3-7a72-9dfe-0011bce8efc8","probe":"What is the maximum tenant improvement allowance amount in dollars?","golden":"$559,160.00","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"}]},{"eval_id":"019de200-d4d4-7185-bf69-9197f90e27ce","probe":"What is the title of Section II?","golden":"TENANT'S WORK","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"}]},{"eval_id":"019de200-d4d5-7ac3-8e4e-c758cbae290a","probe":"What is the per square foot dollar amount mentioned for the Allowance?","golden":"$40.00","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"}]},{"eval_id":"019de200-d4d6-77e1-9296-5f9e11cf7728","probe":"What does item (c) say?","golden":"Intentionally deleted.","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."}]},{"eval_id":"019de200-d4d7-71ee-b89a-13f57933c5ed","probe":"What is the company name shown in the headers of the financial statements?","golden":"Acadia Realty Trust and Subsidiaries","png_sha":"d99abf4bae64753a77c680d1e83acdbdc08eb377e9da9bc0a4af8337f67971e2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"}]},{"eval_id":"019de200-d4d8-73df-b318-56c93e913a1d","probe":"What is the rent payable for December 2016 in the Metroplex Rent table?","golden":"137,399","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"}]},{"eval_id":"019de200-d4d9-7080-91a1-8e4024ae5b27","probe":"What is the title of Exhibit M?","golden":"Metroplex Rent","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex Rent"}]},{"eval_id":"019de200-d4da-740b-af0a-30cdbbdc3a00","probe":"What is the rent payable for July 2018?","golden":"145,763","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"}]},{"eval_id":"019de200-d4db-76f8-b9cf-eb901aaef607","probe":"What is the title of Exhibit N?","golden":"Exclusions From Operating Expenses","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"}]},{"eval_id":"019de200-d4dc-76d9-b19c-2bb2f2c2d455","probe":"What is the rent payable for March 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4dd-7a8e-97e8-6cbb97c9f288","probe":"What is the rent payable for January 2018?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4de-7510-a1bb-a2200cf532b1","probe":"What is the rent payable for May 2018?","golden":"145,763","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"}]},{"eval_id":"019de200-d4df-72db-b8e2-5470717b76c7","probe":"What is the rent payable for September 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4e0-7497-8998-04b404a57589","probe":"What is listed as item (i) under Excluded Expenses in Exhibit N?","golden":"Real Estate Taxes","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"}]},{"eval_id":"019de200-d4e1-704d-bad7-731b3da45bdf","probe":"What is the rent payable for November 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4e2-7aab-ae79-29c74e645fca","probe":"What is the title of Exhibit C?","golden":"Technology Exhibit","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"}]},{"eval_id":"019de200-d4e3-7937-8135-40c4b4f0cb8e","probe":"What is the markup percentage on outgoing mail?","golden":"10%","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"}]},{"eval_id":"019de200-d4e4-7765-86d5-d5fb371119ed","probe":"What is the title of Exhibit B?","golden":"Summit Billing Information","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"}]},{"eval_id":"019de200-d4e5-7bb2-9e8d-5d17eac142de","probe":"What is the reconnection fee per hour mentioned in Exhibit C?","golden":"$100","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"}]},{"eval_id":"019de200-d4e6-7499-90b0-274586c057d5","probe":"What are the standard business hours listed for Summit's remedial maintenance?","golden":"9:00 am to 5:00 pm, Monday - Friday","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"}]},{"eval_id":"019de200-d4e7-7aba-997b-697fce37c98b","probe":"Who signed as Chief Executive Officer of 1847 Holdings LLC?","golden":"Ellery W. Roberts","png_sha":"17421f00db7e68e09f420ba5abd403a8bc79b47f8f380327515bff5297f38fed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"}]},{"eval_id":"019de200-d4e8-7f62-96ae-519b14f37f5f","probe":"On what day of December 2024 did the Guarantors execute this Guaranty?","golden":"13th","png_sha":"17421f00db7e68e09f420ba5abd403a8bc79b47f8f380327515bff5297f38fed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"}]},{"eval_id":"019de200-d4e9-71c2-9557-1e2c70c1e1fb","probe":"What is the Per RSF Base Rent for the Initial Term?","golden":"$20.50","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"}]},{"eval_id":"019de200-d4ea-7529-926e-f6d2957fdefe","probe":"Who is the Named Tenant?","golden":"2U Harkins Road LLC","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"}]},{"eval_id":"019de200-d4ec-7fff-aceb-46c812561273","probe":"Which floors of the Building are designated as the Must Take Expansion Premises?","golden":"Floors 5, 6 and 7","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6, and 7"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Floors 5, 6 and 7"}]},{"eval_id":"019de200-d4ed-7a5a-bca1-903c35b0c671","probe":"What is the speed limit mentioned in rule 4 of the parking rules?","golden":"5 miles per hour","png_sha":"4a35d25bb27a032bf2661265ea4187cfc0129b1d6aa4a12ae16fc6380aea8e4c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"}]},{"eval_id":"019de200-d4ee-76cd-96ee-560ea13db477","probe":"What are the parking hours listed in rule 1?","golden":"7:30 a.m. to 6:30 p.m., Monday through Friday","png_sha":"4a35d25bb27a032bf2661265ea4187cfc0129b1d6aa4a12ae16fc6380aea8e4c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"}]},{"eval_id":"019de200-d4ef-7bf8-a7ba-27307744e3f9","probe":"What is the 2nd Floor Build-Out Allowance amount?","golden":"$600,000.00","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Six Hundred Thousand and No/100 Dollars ($600,000.00)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"}]},{"eval_id":"019de200-d4f0-7baf-9b58-1e08027b6f0d","probe":"How many RSF is the 2nd Floor Premises calculated as for Base Rent purposes?","golden":"12,000 RSF","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"}]},{"eval_id":"019de200-d4f1-7b08-800d-39648227b1fc","probe":"How many days advance notice must Tenant give for an Acceleration Notice?","golden":"120 days","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"}]},{"eval_id":"019de200-d4f2-7a99-af6e-94a36878aec2","probe":"What is the per-RSF dollar amount used to calculate the Must Take Allowance?","golden":"$46.50","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"}]},{"eval_id":"019de200-d4f3-7347-815c-24a4e9f82950","probe":"In the example, what is the Must Take Allowance for the 7th floor?","golden":"$1,198,611.65","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"}]},{"eval_id":"019de200-d4f4-7dcb-9449-8179714e49d7","probe":"What is the limit of liability for Landlord's commercial general liability insurance?","golden":"$5,000,000 per occurrence","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"}]},{"eval_id":"019de200-d4f5-78f3-8340-3580046edcc8","probe":"What is the each occurrence limit for Personal Injury Liability?","golden":"$9,000,000","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"}]},{"eval_id":"019de200-d4f6-7741-884c-42611e27bcef","probe":"What is the Insured's participation percentage for Personal Injury Liability?","golden":"0%","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"}]},{"eval_id":"019de200-d4f7-7940-b10a-9822b81b3272","probe":"What is the Lobby Renovations Allowance?","golden":"$500,000.00","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"}]},{"eval_id":"019de200-d4f8-7a38-8a19-517016d4b55b","probe":"What is the Initial Build-Out Allowance per RSF?","golden":"$48.00","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"}]},{"eval_id":"019de200-d4f9-7748-a94b-9e4c68688de5","probe":"What is the construction supervision fee percentage Landlord charges on hard construction costs?","golden":"1%","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"}]},{"eval_id":"019de200-d4fa-70fc-b7a8-b9c26c2b14e0","probe":"By what date must Tenant substantially complete the 2nd Floor Build-Out Work?","golden":"April 1, 2018","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"}]},{"eval_id":"019de200-d4fb-7f01-8927-c6d175a34ace","probe":"By what date must Tenant substantially complete the Initial Build-Out Work of the Initial Premises?","golden":"April 1, 2017","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"}]},{"eval_id":"019de200-d4fc-7cca-908f-984e3d8120e7","probe":"What is the umbrella liability each occurrence amount?","golden":"$5,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"}]},{"eval_id":"019de200-d4fd-74c2-abb8-1bb3a38e217c","probe":"What is the medical payments coverage amount?","golden":"$5,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"}]},{"eval_id":"019de200-d4fe-76cb-bdd6-bb011389179c","probe":"What is the fire damage legal liability coverage amount?","golden":"$50,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"}]},{"eval_id":"019de200-d4ff-7fd5-9027-7197160465a2","probe":"What is the automobile liability combined single limit amount?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d500-7cfe-8ff2-d8bbbb64073a","probe":"What is the bodily injury by accident coverage amount per accident under Workers' Compensation Coverage B?","golden":"$500,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"}]},{"eval_id":"019de200-d501-782d-845b-a4e35e143c20","probe":"What is the combined single limit per occurrence for Coverage A under Commercial General Liability?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d502-7a8b-9ba6-c9892e2eeecc","probe":"What insurance form is the general liability insurance to be written on?","golden":"2001 Insurance Services Office form","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form or its equivalent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form or its equivalent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form or its equivalent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"}]},{"eval_id":"019de200-d503-798a-afa1-45a2677f34db","probe":"What is the personal and advertising injury liability (Coverage B) amount?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d504-70ea-9d31-b199175fed3c","probe":"In what geographic area must business interruption insurance match amounts customarily carried by responsible tenants?","golden":"Greater Boston","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"}]},{"eval_id":"019de200-d506-744e-be70-a75cf629bab5","probe":"What is the non-refundable assignment/sublease review fee?","golden":"$1,500","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"}]},{"eval_id":"019de200-d507-733d-8d8c-87040ba6130c","probe":"How many days does Landlord have to give Tenant a termination notice after submission of the statement?","golden":"30 days","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"}]},{"eval_id":"019de200-d509-782f-8cb5-81249701c47f","probe":"What percentage of the excess must Tenant pay to Landlord as Assignment/Sublease Excess Rent?","golden":"100%","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"}]},{"eval_id":"019de200-d50a-7a93-8a69-a34202f99ee3","probe":"What is the term used for the portion of Premises eliminated under the Elimination Period?","golden":"Eliminated Space","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""}]},{"eval_id":"019de200-d50b-714d-a6f0-8fbb3c33bc67","probe":"What is the term defined for the date immediately prior to the effective date of the proposed assignment?","golden":"Earlier Termination Date","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""}]},{"eval_id":"019de200-d50c-743d-ad76-780e2c2fb12d","probe":"What is the term used for the period after the Elimination Period during which the Eliminated Space is restored to the Premises?","golden":"Restoration Period","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Restoration Period\""},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Restoration Period\""},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Restoration Period\""},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Restoration Period\""},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Restoration Period\""},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Restoration Period\""},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"}]},{"eval_id":"019de200-d50d-7c5f-a9f2-1705d2b33bc2","probe":"What is the term defined for the consideration payable by the assignee or subtenant?","golden":"Assignment/Sublease Consideration","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""}]},{"eval_id":"019de200-d50f-730f-bba3-567d098ebd36","probe":"By what time each weekday must the stainless steel tops on the 18th Street light boxes be wiped down?","golden":"8:00 AM","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"}]},{"eval_id":"019de200-d510-7320-b95d-f545ed219bc5","probe":"How often must window frames and ledges be swept with a soft-bristled brush on the building exterior?","golden":"Monthly","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"}]},{"eval_id":"019de200-d511-7272-9565-2412f58e253c","probe":"How often must service area floors be dust mopped, at minimum?","golden":"Once per week","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No less than once per week"}]},{"eval_id":"019de200-d512-7496-808b-5b1ea05ca3f8","probe":"How often must standpipe fire hose connections on the exterior of the building be cleaned and polished?","golden":"Weekly","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"}]},{"eval_id":"019de200-d513-7149-ae8c-e8a7754d572b","probe":"What is the minimum amount for a partial prepayment of Revolving Loans?","golden":"$100,000","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"}]},{"eval_id":"019de200-d514-76a5-be6d-0713d4261c08","probe":"What is the full deadline (both time of day and number of business days) by which a Notice of Borrowing must be delivered before a proposed borrowing?","golden":"1:00 p.m. (Eastern time) two (2) Business Days prior","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"}]},{"eval_id":"019de200-d516-7459-9245-cc659422a55c","probe":"By what time on the Termination Date must the entire outstanding principal of each Revolving Loan be paid?","golden":"12:00 Noon (Eastern time)","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"}]},{"eval_id":"019de200-d517-7577-ad4f-c469f0a5f3e3","probe":"What is the higher integral multiple required for partial prepayments of Revolving Loans?","golden":"$25,000","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"}]},{"eval_id":"019de200-d519-76a9-b52e-17fb3cd3da08","probe":"What rate do Revolving Loans accrue interest at, plus the Applicable Margin?","golden":"LIBOR Rate","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"}]},{"eval_id":"019de200-d51a-7cbd-841b-aa945ef2b4a8","probe":"Notices of Borrowing must be delivered before what time (Eastern time)?","golden":"1:00 p.m.","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."}]},{"eval_id":"019de200-d51b-7404-9feb-b6384f640f1a","probe":"How many calendar days prior to lease termination must the parties allow Lessor to enter the property for inspection?","golden":"60","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"}]},{"eval_id":"019de200-d51c-7dd7-ad07-e2fd96baf505","probe":"Who conducted the Phase I Environmental Assessment mentioned in section 11.1?","golden":"GAIM REGIOMONTANA","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"}]},{"eval_id":"019de200-d51d-7bbb-9bed-8ceaca14c398","probe":"What is the telephone number listed for Mr. Juan Carlos Gonzalez Quezada?","golden":"(81) 8358.7978","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"}]},{"eval_id":"019de200-d51e-7caf-b475-352d47499736","probe":"What is the postal code (C.P.) listed in the address for Mr. Juan Carlos Gonzalez Quezada?","golden":"66220","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"}]},{"eval_id":"019de200-d51f-723d-9741-37784d76009a","probe":"What is the telephone number listed for Mr. David Rodriguez Santos at Torre Sienna?","golden":"(81) 8356.1200","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"}]},{"eval_id":"019de200-d520-7d78-a11e-ce881c0ff357","probe":"How many calendar days does Lessor have to object to a proposed sublease in writing?","golden":"30","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"}]},{"eval_id":"019de200-d521-77a9-8367-9a4a834e7041","probe":"What is the apartment/interior number (Int.) listed in the address for Torre Sienna?","golden":"1403","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"}]},{"eval_id":"019de200-d522-7ac9-8bba-7b83fb15043b","probe":"What exhibit is the 'Maintenance Carnet' attached as?","golden":"Exhibit \"J\"","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""}]},{"eval_id":"019de200-d524-75fd-bff6-f429befeae8a","probe":"How many calendar days does Lessee have to dispute damages or Alterations indicated in Lessor's notice?","golden":"15","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"}]},{"eval_id":"019de22d-8775-7482-9f31-5e7710938d70","probe":"What is the original principal amount of the 3.50% Series A Convertible Senior Notes due February 1, 2018?","golden":"$70.3 million","png_sha":"9999d442e3243c2ea48a7de6c4c9b162568b4e59e41492087837bdb419a11d2c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"}]},{"eval_id":"019dfae7-e8c3-7289-a5e3-25d26a497795","probe":"What is the fiscal year end date?","golden":"September 28, 2024","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"}]},{"eval_id":"019dfae8-2c75-7590-9083-4c07bf26944a","probe":"What is the Commission File Number?","golden":"001-36743","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"}]},{"eval_id":"019dfae8-8300-75b0-98f0-558c886fd068","probe":"What is the registrant's telephone number?","golden":"(408) 996-1010","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"}]},{"eval_id":"019dfae8-d37e-73db-bad0-7dbbebba1d87","probe":"What is the IRS Employer Identification Number?","golden":"94-2404110","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"}]},{"eval_id":"019dfae9-3119-7c26-b2ed-73fb2888fdfe","probe":"What is the par value per share of Apple's common stock?","golden":"$0.00001","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"}]},{"eval_id":"019dfae9-c244-75c3-92a8-4f02d64471e6","probe":"What were Americas net sales in 2024 (in millions)?","golden":"$167,045","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"}]},{"eval_id":"019dfaea-1b4b-7bef-bf30-f8f1ee1cb9d6","probe":"What were Europe net sales in 2024 (in millions)?","golden":"$101,328","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$101,328"}]},{"eval_id":"019dfaea-c282-7bca-85d8-a2edb7306504","probe":"What were total net sales in 2024 (in millions)?","golden":"$391,035","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$391,035"}]},{"eval_id":"019dfaeb-1b0e-7077-a093-a8a138a79e25","probe":"What were Greater China net sales in 2022 (in millions)?","golden":"$74,200","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74,200"}]},{"eval_id":"019dfaec-3d80-7c7c-95b7-6a34a086d48b","probe":"What is the date the report was signed?","golden":"November 1, 2024","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"}]},{"eval_id":"019dfaec-8345-7eea-8840-6867945a7a06","probe":"Who is the Director and Chair of the Board?","golden":"Arthur D. Levinson","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"}]},{"eval_id":"019dfaec-e961-7051-a4ce-b66996997cb2","probe":"Who is the Senior Director of Corporate Accounting?","golden":"Chris Kondo","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"}]},{"eval_id":"019dfaed-c27e-7590-9034-1cc2a5319b55","probe":"Who is the accounting firm that signed this consent?","golden":"Ernst & Young LLP","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"}]},{"eval_id":"019dfaee-6467-74cc-8101-5271bea3e394","probe":"What is the Form S-8 number for the Apple Inc. Employee Stock Purchase Plan?","golden":"333-203698","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"}]},{"eval_id":"019dfaf0-11d2-70d1-be50-371940478750","probe":"Where is Braeburn Capital, Inc. incorporated?","golden":"Nevada, U.S.","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."}]},{"eval_id":"019dfaf0-52d8-7941-b336-19bfbe7f8bc1","probe":"Where is Apple Asia Limited incorporated?","golden":"Hong Kong","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"}]},{"eval_id":"019dfaf1-05a1-718d-818a-e45ba4945ba1","probe":"Where is Apple Operations Mexico, S.A. de C.V. incorporated?","golden":"Mexico","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"}]},{"eval_id":"019dfaf2-2642-7eae-b1fb-1620be9706bc","probe":"Starting on what date does this policy apply to Incentive-Based Compensation that is Received?","golden":"October 2, 2023","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"}]},{"eval_id":"019dfaf3-1977-7337-8a56-6b3d55edd900","probe":"What Nasdaq listing rule was adopted to implement Rule 10D-1 under the Exchange Act?","golden":"Listing Rule 5608","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"}]},{"eval_id":"019dfaf3-d93a-7e7a-8293-bed401dc3c74","probe":"Under what year's Securities and Exchange Act is 'executive officer' defined for this policy?","golden":"1934","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"}]},{"eval_id":"019dfaf4-6d06-7bb4-9da0-5703eced16ad","probe":"What company's logo appears at the top of this policy?","golden":"Apple","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"}]},{"eval_id":"019dfaf5-67bd-727d-92f0-43a3108e55cf","probe":"What is the commission file number?","golden":"001-37580","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"}]},{"eval_id":"019dfaf5-e414-73d4-a5bb-864069d83389","probe":"What is the IRS Employer Identification Number?","golden":"61-1767919","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"}]},{"eval_id":"019dfaf6-3c67-7437-b33f-106a71df96cc","probe":"What is the registrant's telephone number?","golden":"(650) 253-0000","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"}]},{"eval_id":"019dfaf6-8eaf-75f8-a68a-e019cf9ab6dc","probe":"What is the interest rate of the Senior Notes due 2064?","golden":"4.375%","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"}]},{"eval_id":"019dfaf6-cd98-71f2-9576-0e07833ebd70","probe":"What is the interest rate of the Senior Notes due 2028?","golden":"2.375%","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"}]},{"eval_id":"019dfaf7-7376-72e6-af9f-4f0302bf05aa","probe":"What is the trading symbol for Alphabet's Class C Capital Stock?","golden":"GOOG","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"}]},{"eval_id":"019dfaf7-a3e9-7079-abc1-1170e6a73c4f","probe":"What is the fiscal year end date on this 10-K?","golden":"December 31, 2025","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"}]},{"eval_id":"019dfaf8-7549-77d5-b050-b8468d035af7","probe":"What was the total amount of Class C share repurchases for the three months ended March 31, 2025?","golden":"$12,535 million","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"}]},{"eval_id":"019dfaf8-f7e3-7fa2-809d-07b2ec3cfaea","probe":"How much remained available for Class A and Class C share repurchases as of March 31, 2025?","golden":"$29.5 billion","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"}]},{"eval_id":"019dfafa-9cb0-7412-8eac-d16591d94510","probe":"What is the quarterly cash dividend declared on April 2025?","golden":"$0.21","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"}]},{"eval_id":"019dfafb-3912-792d-bc47-54ca00054b5c","probe":"What were the revenues for 2025?","golden":"$402,836 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"}]},{"eval_id":"019dfafb-834e-72a8-893b-436ffbf094a2","probe":"What was the net income for 2024?","golden":"$100,118 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"}]},{"eval_id":"019dfafc-94fe-761b-9254-9f753ab96d14","probe":"What was the total amount of share repurchases for the nine months ended September 30, 2025?","golden":"$40,117 million","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"}]},{"eval_id":"019dfafd-0e8d-7a0f-8f4e-4d3d489b698a","probe":"By what percentage did the Board of Directors increase the quarterly cash dividend in April 2025?","golden":"5%","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"}]},{"eval_id":"019dfafe-5a0c-7b21-8bfa-72a257476e5a","probe":"What was the total carrying value of senior unsecured notes outstanding as of September 30, 2025?","golden":"$23.6 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"}]},{"eval_id":"019dfaff-051e-7ba2-8350-09ebbfdb115a","probe":"How much remained available for Class A and Class C share repurchases as of September 30, 2025?","golden":"$74.8 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"}]},{"eval_id":"019dfb00-8129-7fae-9c3d-085f17af7163","probe":"How many Class C shares were repurchased in the three months ended September 30, 2025 (in millions)?","golden":"51","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"}]},{"eval_id":"019dfb01-6670-7c43-bf57-578d4e8743df","probe":"How much was the revolving credit facility expiring in April 2030?","golden":"$6.0 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"}]},{"eval_id":"019dfb02-8211-7651-9ec4-8c0ebcf58a3b","probe":"What was the dollar amount of Class A share repurchases for the three months ended September 30, 2025 (in millions)?","golden":"$926","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"}]},{"eval_id":"019dfb06-2d63-7e40-9cfc-442adddd3a61","probe":"As of what date did the CEO and CFO conclude on the disclosure controls evaluation?","golden":"June 30, 2025","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"}]},{"eval_id":"019dfb06-7255-7580-9ef1-58f24ae75626","probe":"What rule under the Exchange Act was used to evaluate disclosure controls and procedures?","golden":"Rule 13a-15","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"}]},{"eval_id":"019dfb07-58e1-741b-95ae-39f6ad5b9738","probe":"For what quarter ended date is the internal control reporting statement made?","golden":"June 30, 2025","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"}]},{"eval_id":"019dfb08-723b-72c9-8209-4c6b104c74d9","probe":"What form is the Quarterly Report on?","golden":"Form 10-Q","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"}]},{"eval_id":"019dfb09-b2b4-7900-94d0-5ead62b5fa3a","probe":"How much was the initial investment used in the graph comparison?","golden":"$100","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"}]},{"eval_id":"019dfb0a-1542-7607-afff-3824643328be","probe":"On what date does the graph's tracking period end?","golden":"December 31, 2025","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"}]},{"eval_id":"019dfb0a-4250-7161-8e90-fa2502ad8254","probe":"What is the starting date of the graph's tracking period?","golden":"December 31, 2020","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"}]},{"eval_id":"019dfb0a-bbec-7b6d-bb26-274ff05f9459","probe":"What is the highest dollar value shown on the y-axis of the graph?","golden":"$400","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"}]},{"eval_id":"019dfb0a-e54b-7973-8d05-99144d938deb","probe":"What color is the line representing the S&P 500 in the graph?","golden":"Green","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"}]},{"eval_id":"019dfb0b-0fe9-717a-b315-903647d9114e","probe":"What color is the line representing Alphabet Inc. Class C in the graph?","golden":"Red","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"}]},{"eval_id":"019dfb0b-9664-7b20-bea5-647276953368","probe":"How much is Alphabet acquiring Wiz, Inc. for?","golden":"$32.0 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"}]},{"eval_id":"019dfb0c-07a8-768c-bf46-7d82769ad116","probe":"What is the long-term income taxes payable as of December 31, 2025?","golden":"$9.5 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"}]},{"eval_id":"019dfb0d-123a-74db-8a55-4a162b6b8cfb","probe":"How much is Alphabet acquiring Intersect for in cash?","golden":"$4.8 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"}]},{"eval_id":"019dfb0d-98a6-7573-8987-ba32c57f6b7a","probe":"What is the total amount of purchase commitments and other contractual obligations as of December 31, 2025?","golden":"$149.1 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"}]},{"eval_id":"019dfb0e-3ccc-74fa-9d0d-91c2663bea11","probe":"What was the total revenue for the three months ended March 31, 2025?","golden":"$90,234 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"}]},{"eval_id":"019dfb0e-aa32-78f0-b197-81311a562d15","probe":"What were the total long-lived assets in the United States as of March 31, 2025?","golden":"$149,304 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"}]},{"eval_id":"019dfb0f-11dc-7143-87ab-1b18f0a0c5b8","probe":"What was Google Cloud's operating income for the three months ended March 31, 2025?","golden":"$2,177 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"}]},{"eval_id":"019dfb10-1fb2-7986-b06c-55501bbd796e","probe":"What was the United States revenue for the three months ended September 30, 2025?","golden":"$48,758 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"}]},{"eval_id":"019dfb10-c712-7d30-9f15-c857b9160151","probe":"What was the EMEA revenue for the nine months ended September 30, 2025?","golden":"$84,096 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"}]},{"eval_id":"019dfb11-2196-7673-aeb2-eebcf53e53b2","probe":"What was the APAC revenue for the three months ended September 30, 2024?","golden":"$14,547 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"}]},{"eval_id":"019dfb11-8ce1-72d9-b0ab-fc0be563e187","probe":"What were the total revenues for the nine months ended September 30, 2025?","golden":"$289,007 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"}]},{"eval_id":"019dfb14-6817-7cc7-90e2-fce76cd476e7","probe":"How many employees did JPMorganChase have globally as of December 31, 2025?","golden":"318,512","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"}]},{"eval_id":"019dfb14-a085-7b52-8f76-6678f2a4de9c","probe":"How many employees does JPMorganChase have in North America?","golden":"185,208","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"}]},{"eval_id":"019dfb14-f2e3-7cee-a27e-79e81867b37a","probe":"How many employees work in CCB?","golden":"144,196","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"}]},{"eval_id":"019dfb15-3908-7fc5-93bd-052705ae9929","probe":"In how many countries are JPMorganChase's employees located?","golden":"66","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"}]},{"eval_id":"019dfb15-75a7-7c29-a2ca-90c32df63ac5","probe":"What percentage of total employees are women?","golden":"48%","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"}]},{"eval_id":"019dfb15-c7c7-74ee-b29b-e7b5d8c9a152","probe":"How many employees work in the Asia-Pacific region?","golden":"96,499","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"}]},{"eval_id":"019dfb16-cbe3-7d4d-a23d-2234c2d7d297","probe":"What is the first bulleted item under the list of electronic and internet-based financial solutions?","golden":"lending and other extensions of credit to consumers","png_sha":"704943f48019c6bab8cb509e1ddeb6f9b48085007ac9101976ed3d04798ac274","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lending and other extensions of credit to consumers"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lending and other extensions of credit to consumers"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lending and other extensions of credit to consumers"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"}]},{"eval_id":"019dfb17-0cc4-74a1-8d62-afab29ef1e82","probe":"What is the third bulleted item under the list of electronic and internet-based financial solutions?","golden":"cryptocurrency, including stablecoins","png_sha":"704943f48019c6bab8cb509e1ddeb6f9b48085007ac9101976ed3d04798ac274","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"}]},{"eval_id":"019dfb18-cb9a-7558-a5ce-7b4911abc1ba","probe":"What was the total assets under management in 2025 (in billions)?","golden":"$4,791","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"}]},{"eval_id":"019dfb19-eada-7639-80c1-d416915f2795","probe":"How many client advisors were there as of December 31, 2025?","golden":"10,150","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"}]},{"eval_id":"019dfb1a-7fed-744e-a7bc-585de30578fb","probe":"What was the equity assets value in 2025 (in billions)?","golden":"$1,400","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400"}]},{"eval_id":"019dfb1a-d4b4-7ee1-b950-3f3208c24be4","probe":"What was the reported net interest income in 2025 (in millions)?","golden":"$95,443","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"}]},{"eval_id":"019dfb1b-4a0a-766a-92cd-c2e37df27c36","probe":"What was the net yield on average interest-earning assets on a managed basis in 2025?","golden":"2.50%","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"}]},{"eval_id":"019dfb1b-9e1c-704c-b958-e7a06540c65f","probe":"What was the Memo: Total Markets net revenue in 2025 (in millions)?","golden":"$35,782","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"}]},{"eval_id":"019dfb1c-4c58-739f-8241-e4a688fff415","probe":"What was the noninterest revenue excluding Markets in 2023 (in millions)?","golden":"$44,361","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"}]},{"eval_id":"019dfb1d-0b1b-7540-9211-41f0ac069d15","probe":"In what year was MetLife, Inc. incorporated in Delaware?","golden":"1999","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"}]},{"eval_id":"019dfb1d-fe01-7745-a248-c6531ebdce43","probe":"What act is referenced as the source of the 'forward-looking statements' definition?","golden":"Private Securities Litigation Reform Act of 1995","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"}]},{"eval_id":"019dfb1e-4042-7d24-95d6-9213cb5fb946","probe":"How many factors are listed on this page?","golden":"22","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"}]},{"eval_id":"019dfb1e-d54d-73fd-8f17-16eb21390c86","probe":"What is factor number 10 in the list?","golden":"London Interbank Offered Rate discontinuation and transition to alternative reference rates","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"}]},{"eval_id":"019dfb1f-5f66-79ad-be34-3c4e429dbcac","probe":"How old is Steven J. Goulart?","golden":"64","png_sha":"8a8df5c53ffc88bd982b700c7adc729d6f1a78da7ebcbf1ee0a1a778e2017590","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"}]},{"eval_id":"019dfb22-1d21-7795-bb3e-bdc661245cb9","probe":"What is the % of Total for Aaa/Aa/A rated securities as of December 31, 2021?","golden":"70.4%","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"}]},{"eval_id":"019dfb23-4f44-7d83-91d3-79100e6cffec","probe":"What were the adjusted earnings available to common shareholders for the U.S. segment?","golden":"$2,996 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"}]},{"eval_id":"019dfb23-8371-717a-825f-6e20e45dcb5f","probe":"What is the U.S. segment's percentage contribution to total segment level adjusted earnings?","golden":"47%","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"}]},{"eval_id":"019dfb23-d976-764b-875f-1c7d8d24b80e","probe":"What were the adjusted earnings for the Asia segment?","golden":"$1,378 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"}]},{"eval_id":"019dfb24-353e-721c-af95-7c83f5c7c811","probe":"What were the adjusted earnings for the EMEA segment?","golden":"$246 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"}]},{"eval_id":"019dfb25-429c-7aee-a55e-43ed0574b742","probe":"What is the estimated fair value of policyholder account balances?","golden":"$115,408 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"}]},{"eval_id":"019dfb25-8392-72a3-af31-c1805d75def2","probe":"What is the estimated fair value of equity securities?","golden":"$1,684 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"}]},{"eval_id":"019dfb26-154c-7462-80c9-ac925ac520e6","probe":"What is the notional amount of foreign currency swaps?","golden":"$56,025 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"}]},{"eval_id":"019dfb29-7d6d-77ed-abe1-9e196503fe98","probe":"What is American Life Insurance Company's Moody's rating?","golden":"A1","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"}]},{"eval_id":"019dfb29-d233-7190-9c54-414c50184509","probe":"What is Metropolitan Life Insurance Company's Fitch rating?","golden":"AA-","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"}]},{"eval_id":"019dfb2a-30eb-73bc-9534-9a1a79fcefd9","probe":"What is Metropolitan Tower Life Insurance Company's Moody's rating?","golden":"Aa3","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3, 4th of 21"}]},{"eval_id":"019dfb3c-0056-7fd4-8497-80ad7e52deed","probe":"What is the date on the letter?","golden":"September 12, 2025","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"}]},{"eval_id":"019dfb3c-443c-749d-9922-e22f48da574a","probe":"What is the total amount of expenses stated in the letter?","golden":"$537.6 billion","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"}]},{"eval_id":"019dfb3c-e409-7e70-93e0-584a7b66e218","probe":"What is the fax number listed at the bottom of the letter?","golden":"916.322.4404","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"}]},{"eval_id":"019dfb3d-df1d-70c3-8680-871f110c4e18","probe":"How many state departments are involved in the ACFR production, according to the letter?","golden":"more than 200","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"}]},{"eval_id":"019dfb41-090f-742c-a295-a841b0d40942","probe":"What is the last year the ACFR publication target date in March was achieved, according to the letter?","golden":"2018","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"}]},{"eval_id":"019dfb42-0697-72fe-ace9-658c5975fe72","probe":"What is the General fund balance as previously reported on 6/30/2023?","golden":"$64,003,688","png_sha":"4d385e9f1f0ded0edf6cd42e1fce98d308714a9c9a90264d60830da6a87b20a5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 (thousands)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 (thousands)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 (thousands)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 (thousands)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 (thousands)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688 thousand"}]},{"eval_id":"019dfb42-9508-70e6-ba0b-e32a83de1982","probe":"What is the Pension/OPEB balance as previously reported on 6/30/2023?","golden":"$826,165,564","png_sha":"4d385e9f1f0ded0edf6cd42e1fce98d308714a9c9a90264d60830da6a87b20a5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (in thousands)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 thousand"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564 (thousands)"}]},{"eval_id":"019dfb45-009b-71c5-a560-66fa6f28c0b7","probe":"What were the personal income taxes for 2024?","golden":"$116.5 billion","png_sha":"be9e4b96b82c2251ae314ddc72ad643547069399fbff67cb23663b4b60410b07","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"}]},{"eval_id":"019dfb45-c922-797e-8c28-c8e8919e6e6b","probe":"What was the General Fund's ending fund balance for fiscal year 2023-24?","golden":"$63.4 billion","png_sha":"be9e4b96b82c2251ae314ddc72ad643547069399fbff67cb23663b4b60410b07","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"}]},{"eval_id":"019dfb48-c7e6-72a9-8f31-8e936894de0c","probe":"What was the total primary government net position in 2006 (in thousands)?","golden":"$48,552,143","png_sha":"6ded8b72d8724efb0a5addcabb85b9fb055c8702b034b32a8bd9d35ae7b3b2d4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143 thousand"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143 (thousands)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143 (thousands)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143 (thousands)"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143 (thousands)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"}]},{"eval_id":"019dfb49-36d0-787d-9b10-263d0dc86158","probe":"What was the total business-type activities net position in 2005 (in thousands)?","golden":"$9,638,143","png_sha":"6ded8b72d8724efb0a5addcabb85b9fb055c8702b034b32a8bd9d35ae7b3b2d4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"}]},{"eval_id":"019dfb49-c621-751e-8311-221426895f61","probe":"What date does the fiscal year end?","golden":"June 30, 2013","png_sha":"e78f4e20277a031b7f8a1c8ec01e35359d5db802026c772a280aa46b2e15036d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"}]},{"eval_id":"019dfb4a-c5b5-77b8-8666-73fe5ecf7295","probe":"What word appears on the banner above the figure in the seal?","golden":"EUREKA","png_sha":"e78f4e20277a031b7f8a1c8ec01e35359d5db802026c772a280aa46b2e15036d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eureka"}]},{"eval_id":"019dfb4c-a89f-7747-8ca3-fb374afbe129","probe":"How many employees were in the Services industry in 2012?","golden":"6,219,000","png_sha":"ee102138e4471a718761ff29297490e756f20be442c4eab71f74ad7b88ef9337","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"}]},{"eval_id":"019dfb4d-3d6b-7988-bb66-c81ee4e34bf7","probe":"How many employees were in Manufacturing in 2003?","golden":"1,544,500","png_sha":"ee102138e4471a718761ff29297490e756f20be442c4eab71f74ad7b88ef9337","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"}]},{"eval_id":"019dfff9-bbf0-7f8f-9eeb-4283d498732d","probe":"What is the General Fund amount due from primary government to University of California?","golden":"$169,215","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 thousand"}]},{"eval_id":"019dfffa-4c63-71d9-9bae-44bb0f5d067a","probe":"What is the total primary government amount due to component units?","golden":"$209,125","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 thousand"}]},{"eval_id":"019dfffa-9fa6-7a63-a87b-53eda9047796","probe":"What is the amount from Nonmajor governmental funds due to University of California?","golden":"36,988","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"}]},{"eval_id":"019dfffb-b244-7a37-903d-2e6addf12282","probe":"What was the net general bonded debt per capita in 2018?","golden":"$2,042","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"}]},{"eval_id":"019dfffc-0d62-7f14-a566-4e70db84b399","probe":"What was the net general bonded debt as a percentage of personal income in 2015?","golden":"4.0%","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"}]},{"eval_id":"019dfffc-678a-79c5-aaea-473c3f22a054","probe":"What was the General obligation bonds amount in 2017?","golden":"$79,503,871","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871 (thousands)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871 (thousands)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"}]},{"eval_id":"019dfffc-e4bf-79ad-8c4e-89d704ac54ed","probe":"What is at the top of the Texas government structure chart?","golden":"The Electorate","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"}]},{"eval_id":"019dfffd-a1d4-7a49-94b8-3ef9aa5497d4","probe":"What are the two highest courts shown under the Judicial branch?","golden":"The Supreme Court of Texas and The Court of Criminal Appeals","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"}]},{"eval_id":"019dfffe-6b06-706f-a135-e5934397dcc8","probe":"What body sits directly below the Legislature on the chart, alongside the State Auditor's Office?","golden":"Legislative Committees","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"}]},{"eval_id":"019dffff-131f-7d34-8e0c-2be25da41c0d","probe":"What two courts are shown at the bottom level under County-Level Courts?","golden":"Municipal Courts and Justice of the Peace Courts","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"}]},{"eval_id":"019dffff-a90b-7567-a8fa-d73e11996c14","probe":"What body is shown at the very bottom of the Legislative branch chart?","golden":"Sunset Advisory Commission","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"}]},{"eval_id":"019e0000-52c3-755e-9a98-534e00107784","probe":"What is the total pass-through to other agencies?","golden":"$254,334.30","png_sha":"cee789f33becc6e55d762115a7b119808f36099b5c736f4b0ec740bce52a004c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"}]},{"eval_id":"019e0001-dddd-7fec-b736-f93ff293500f","probe":"What was the balance in the ESF fund on Aug. 31, 2024?","golden":"$23.8 billion","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"}]},{"eval_id":"019e0002-846c-7a5c-bcd2-21cf9dab8b63","probe":"What was the Texas unemployment rate as of November 2024?","golden":"4.2 percent","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"}]},{"eval_id":"019e0003-4dd3-73ec-8ba4-bf652587ad06","probe":"By how much is Texas' population projected to grow in 2025?","golden":"376,600","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"}]},{"eval_id":"019e0008-27fa-70f4-8421-41777f7bcace","probe":"What office is shown in pink under the First Deputy Mayor?","golden":"Office of Efficiency","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"}]},{"eval_id":"019e0009-2f8e-768d-8762-ff9e82bcea2b","probe":"What is the SAO Report Number?","golden":"25-316","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"}]},{"eval_id":"019e0009-af38-766a-9ac7-cb0908ad2999","probe":"What percent of the assets of the Colleges and Universities does the University of Texas System constitute?","golden":"72.9 percent","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"}]},{"eval_id":"019e000a-7052-7138-b0db-733f874d02cd","probe":"What percent of the expenditures for the State Highway Fund does the Texas Department of Transportation constitute?","golden":"99.9 percent","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"}]},{"eval_id":"019e000b-683c-7e54-aaf2-3d634ac03517","probe":"What is the total expenses for Education in Graph MDA-5?","golden":"$46,073 million","png_sha":"3f8e2c78a2134ddb79f740cc731c989a29e5b11d89cdb0254e1f1740d44cfdb0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"}]},{"eval_id":"019e000b-d49b-7660-82c4-81ecfb04a236","probe":"What percentage of revenue comes from Charges for Services in Graph MDA-6?","golden":"59.7%","png_sha":"3f8e2c78a2134ddb79f740cc731c989a29e5b11d89cdb0254e1f1740d44cfdb0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"}]},{"eval_id":"019e000d-e61a-7a45-b84f-1c881c74e271","probe":"What is the fair value of Private Equity investments (in thousands)?","golden":"$76,309,756","png_sha":"1993d56fb3f7471f5844aa6a62bb8dd9a43b4784dac30f107664bca458bf68ea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"}]},{"eval_id":"019e000e-f859-77f7-aa7c-927c51e130e8","probe":"What is the unfunded commitment for Energy, Natural Resources, Infrastructure (in thousands)?","golden":"$11,460,123","png_sha":"1993d56fb3f7471f5844aa6a62bb8dd9a43b4784dac30f107664bca458bf68ea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$11,460,123"}]},{"eval_id":"019e0010-c825-72aa-a139-0e4ab295b2dc","probe":"What is the minimum aggregate floor area required by the CEP program?","golden":"25,000 square feet","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"}]},{"eval_id":"019e0011-2a92-7ac7-89be-ac4f2296baea","probe":"Under the CRP/CEP programs, by how much were the City's tax revenues reduced in 2024 (in thousands)?","golden":"$12,500","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"}]},{"eval_id":"019e0011-cff1-7126-8235-02b26f0fbab9","probe":"What year did ICAP replace ICIP?","golden":"2008","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"}]},{"eval_id":"019e0017-450f-737d-a346-38c48007c835","probe":"Under the CRP program, what is the per-square-foot dollar amount used in the base abatement calculation formula?","golden":"$2.50","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"}]},{"eval_id":"019e0018-17a0-7847-a0b3-11f039bc48a6","probe":"What is the page number shown at the bottom of this page?","golden":"128","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"}]},{"eval_id":"019e0019-d170-7146-8e38-cc44276e6018","probe":"Under the CRP/CEP programs, by how much were the City's tax revenues reduced as a result of abatement agreement in 2024 (in thousands)?","golden":"$12,500","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"}]},{"eval_id":"019e001b-3183-79f1-a745-4e066a6ce3ef","probe":"What is the Executive Order number mentioned in the letter?","golden":"2025-1","png_sha":"781c6fcbd4f3164179bf71cd942ca2e9794fc7c49c6bbcf883dd13f2ce626331","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"}]},{"eval_id":"019e001b-77bc-7c11-843b-51dfbbec15c3","probe":"Who signed this letter?","golden":"Mayor Brandon Johnson","png_sha":"781c6fcbd4f3164179bf71cd942ca2e9794fc7c49c6bbcf883dd13f2ce626331","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"}]},{"eval_id":"019e001d-d405-7881-ab8b-abcb0d7e70e1","probe":"What is Deloitte's fax number listed on the page?","golden":"+1 312 486 1486","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"}]},{"eval_id":"019e001f-f83d-78ad-bad5-21b87bdb9833","probe":"According to the auditor's report, the Pension Trust Funds represent what percentages of the assets, financial position, and revenues respectively?","golden":"92%, 100%, and 72%","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"}]},{"eval_id":"019e0020-bffb-7733-931f-63dac6e0f8f0","probe":"Who is the report addressed to as Mayor?","golden":"Brandon Johnson","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"}]},{"eval_id":"019e0027-f41a-7a7a-b3f6-f9b59cde341b","probe":"What is the experience study period for the Policemen's plan?","golden":"January 1, 2019 - December 31, 2023","png_sha":"2aded5f520cbaa023e8d0c1e94f15e68ccafa9f34d1e6736781e6f894512fe8e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"}]},{"eval_id":"019e0028-b45f-7292-959c-f04db8d08d19","probe":"What is the experience study period for the Laborers' plan?","golden":"January 1, 2017 - December 31, 2019","png_sha":"2aded5f520cbaa023e8d0c1e94f15e68ccafa9f34d1e6736781e6f894512fe8e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"}]},{"eval_id":"019e002a-8546-75d0-9290-e4f34687786f","probe":"What year ended is referenced at the top of the page?","golden":"December 31, 2024","png_sha":"4ceaa28bf7551920a1890b7fbf19a27b1cc875ad22828548d20d5021ffb4cb9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"}]},{"eval_id":"019e002e-34d1-7c51-ba48-bffeca76fb26","probe":"What was the loans receivable balance of the CCCF as of December 31, 2024?","golden":"$3.1 million","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"}]},{"eval_id":"019e002e-ef48-7527-8160-cb77c6e44245","probe":"On what date did the City of Chicago City Council adopt the ordinance organizing the STSC?","golden":"October 11, 2017","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"}]},{"eval_id":"019e0030-d1da-7720-bec1-d70663e3456a","probe":"On what date did the City Council adopt the CCCF Ordinance?","golden":"November 16, 2016","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"}]},{"eval_id":"019e0033-8f40-79d7-8505-50112ded8060","probe":"What is the website where complete financial statements of the STSC can be obtained?","golden":"www.salestaxsecuritizationcorporation.com","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"}]},{"eval_id":"019e003a-5da3-7d08-9f15-665248ccb0cf","probe":"What was the final budgeted Vehicle Tax amount under Transportation Tax (in thousands)?","golden":"$128,777","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"}]},{"eval_id":"019e003a-e619-7c9f-b4b2-aa2807d3bff9","probe":"What was the actual Motor Fuel Tax and Project revenue under Transportation Tax (in thousands)?","golden":"$122,483","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$122,483"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$122,483"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"}]},{"eval_id":"019e003c-6cc9-782c-bca0-875bef94c76c","probe":"What was the final budgeted MEABF Pension Reserve under Special Area and Utility Taxes (in thousands)?","golden":"$216,275","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$216,275"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"}]},{"eval_id":"019e003d-55d2-7007-b3b6-dc37892643d2","probe":"Who is the Chief Actuary?","golden":"Marek Tyszkiewicz","png_sha":"89c77daf9c6f881f0116f445cbf736cffc12698b60a93b437699a1a075b00138","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"}]},{"eval_id":"019e003f-44df-7a8d-a15c-ff2dc3cf553b","probe":"What is the funded ratio for the 2022 valuation date?","golden":"85.1%","png_sha":"13c08f8d02fa78d2fc1f1b9783d494af4a43f3083f75509ffac06a9ae415320f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"}]},{"eval_id":"019e0040-0266-795a-b6d2-549f195f8032","probe":"What percentage of the Police Superior Officers' Variable Supplements Fund is held in Collective Trust Funds?","golden":"59.28%","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"}]},{"eval_id":"019e0040-6668-7abd-8cd8-dd05d069c1c1","probe":"What is the dollar amount of Equity Securities in the Police Officers' Variable Supplements Fund?","golden":"$771,119","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"}]},{"eval_id":"019e0041-2237-71d4-8880-cb8564c7b0ae","probe":"What is the dollar amount of Short-Term Investments in the Police Superior Officers' Variable Supplements Fund?","golden":"$8,441","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"}]},{"eval_id":"019e0042-1c07-71d9-8683-e990abab4862","probe":"What is the Reduced Service Retirement probability at 20 years of service?","golden":"5.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"}]},{"eval_id":"019e0043-db39-746e-8a90-d9b8e9e16e2f","probe":"What is the Unreduced Before Full Escalation probability at 22 years of service?","golden":"5.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"}]},{"eval_id":"019e0044-11fe-7039-99f0-4014e1cca342","probe":"What is the Reduced Service Retirement probability at 21 years of service?","golden":"2.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"}]},{"eval_id":"019e0045-18ce-7ff9-90d3-7a8a76d3a7b2","probe":"What is the As Restated Total Liabilities amount?","golden":"54,689,670","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670 (thousands)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$54,689,670"}]},{"eval_id":"019e0046-8a1d-76f7-a894-dfdf17c5e779","probe":"What is the As Previously Stated Unrestricted (Deficit) amount (in thousands of dollars)?","golden":"(33,888,893)","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"}]},{"eval_id":"019e0048-5d8d-7e41-bfac-807538f6bc7d","probe":"What is the required year of adoption for GASB Statement No. 102?","golden":"2025","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"}]},{"eval_id":"019e0049-7334-7204-a87d-cdd77f11d1df","probe":"What is the As Restated Total Net (Deficit)/Position amount (in thousands)?","golden":"$(30,877,248)","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$(30,877,248)"}]},{"eval_id":"019e004a-3183-7f93-ae28-888547cf9f69","probe":"What is the As Previously Stated Accrued and Other Liabilities amount (in thousands)?","golden":"$2,037,352","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"}]},{"eval_id":"019e004b-c349-7e93-af8d-24a8c0227413","probe":"Who is the Chairman of the Texas Transportation Commission?","golden":"J. Bruce Bugg, Jr.","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."}]},{"eval_id":"019e004c-1788-7c26-832d-effce8fee9e9","probe":"What city is Commissioner Robert C. Vaughn from?","golden":"Dallas","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"}]},{"eval_id":"019e004c-7b29-737b-b3c2-4cb5677b686a","probe":"What city is Commissioner Steven D. Alvis from?","golden":"Houston","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"}]},{"eval_id":"019e004e-6fac-7e8f-a9ed-7aab75af118d","probe":"What is the Total Foreign Currency Risk for Fiduciary Funds (in thousands)?","golden":"$454,100","png_sha":"14dd94971a85d5333d42a72d87ae42c4f4cf19684f10114f6d12e3dc0dcfbba3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"}]},{"eval_id":"019e004f-570b-7494-b4dc-1980043719cb","probe":"What is the Component Units amount for Uninsured and Uncollateralized in Table 3A (in thousands)?","golden":"$729,847","png_sha":"14dd94971a85d5333d42a72d87ae42c4f4cf19684f10114f6d12e3dc0dcfbba3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"}]},{"eval_id":"019e0050-7b43-7b4a-b132-8ba0d44ecc08","probe":"What is the Total Fund Balance \u2013 Governmental Funds (in thousands)?","golden":"$98,174,085","png_sha":"2e5b15b0fe9ca40f66bc4f99fea40f7e0fb26c9abe4ac75ea6dad2ab72ae36d6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"}]},{"eval_id":"019e007c-e48c-710f-9404-90a2a810ccb4","probe":"What is the Net Position of Governmental Activities (in thousands)?","golden":"$134,878,410","png_sha":"2e5b15b0fe9ca40f66bc4f99fea40f7e0fb26c9abe4ac75ea6dad2ab72ae36d6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"}]},{"eval_id":"019e007d-9a24-752a-89d4-7fe852700caa","probe":"What is the total revenue shown in the Revenue by Source pie chart?","golden":"$190.5 Billion","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"}]},{"eval_id":"019e007d-e19f-7d15-815d-b4e94383d99b","probe":"What are the total expenses for Health and Human Services?","golden":"$75,194 million","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"}]},{"eval_id":"019e007e-1a80-7e4b-98c2-9c3f2d812c06","probe":"What percentage of revenue came from Taxes?","golden":"42.7%","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"}]},{"eval_id":"019e007e-5b89-72a2-b531-375ac7e4ca75","probe":"What is the dollar amount of Operating Grants and Contributions?","golden":"$74.9 billion","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"}]},{"eval_id":"019e007e-aac9-7785-8c44-edb9f9dfe20d","probe":"What are the total expenses across all governmental activities?","golden":"$154,896","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"}]},{"eval_id":"019e007f-3589-7306-b64b-6253528585e4","probe":"What page is Risk Factors on?","golden":"14","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"}]},{"eval_id":"019e007f-7683-7d10-a251-ff6bdde0aca0","probe":"What page is Executive Compensation on?","golden":"105","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"}]},{"eval_id":"019e007f-b345-710c-b63d-5812e55e82ef","probe":"What page is Financial Statements and Supplementary Data on?","golden":"48","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"}]},{"eval_id":"019e0080-81ba-7bac-bba1-8cc2e8324436","probe":"What page is the Budgetary Comparison \u2013 General Fund on?","golden":"47","png_sha":"0a460adc7db810670c579dc36d27c02a4097bb3e02f77fbbeacd84bbcc9d2f0e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"}]},{"eval_id":"019e0080-b0bf-7f30-a02e-a2ed8dcea371","probe":"What page is the Schedule of Employee Benefits \u2013 All Funds on?","golden":"56","png_sha":"0a460adc7db810670c579dc36d27c02a4097bb3e02f77fbbeacd84bbcc9d2f0e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"}]},{"eval_id":"019e0081-ed0a-7c3a-a9ba-53b6b5920008","probe":"What word is shown as a watermark across the map?","golden":"DRAFT","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"}]},{"eval_id":"019e0082-3d98-723b-b6b4-132e744dab15","probe":"Which county is labeled at the bottom-right area of the map, below Ellis?","golden":"Navarro","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"}]},{"eval_id":"019e0083-0a96-77f4-a106-fb583482c798","probe":"How much did the General Land Office (GLO) increase?","golden":"$860 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"}]},{"eval_id":"019e0083-5461-7354-8851-9512e63b1c22","probe":"How much did the Texas Commission on Environmental Quality (TCEQ) increase?","golden":"$543 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"}]},{"eval_id":"019e0083-c942-7b97-83f8-c0423a20e2a4","probe":"How much did the Federal Emergency Management Agency (FEMA) decrease?","golden":"$420 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"}]},{"eval_id":"019e0084-65de-77d8-92f6-79df23bc1fad","probe":"What is the phone number for Pattillo, Brown & Hill, L.L.P.?","golden":"254.772.4901","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"}]},{"eval_id":"019e0084-dffc-7ecf-b0c1-44b81836ebdd","probe":"What is the date of the year ended for the audit?","golden":"September 30, 2024","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"}]},{"eval_id":"019e009f-5030-795d-b32e-68b8c8725b1a","probe":"What is the page number shown at the bottom right?","golden":"H261","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"}]},{"eval_id":"019e00a0-6d47-7a01-8cdb-9db00cf90181","probe":"Which bill number is referenced as the 'Born-Alive Abortion Survivors Protection Act'?","golden":"H.R. 21","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"}]},{"eval_id":"019e00a1-03cf-7de0-9353-8ede1f29d21e","probe":"What time did the House meet?","golden":"10 a.m.","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."}]},{"eval_id":"019e00a2-46eb-7c4d-93dc-be4b015c5931","probe":"Until what time may morning-hour debate continue?","golden":"11:50 a.m.","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."}]},{"eval_id":"019e00a2-8827-7350-ac1d-d1e691c7bc93","probe":"Which Congress's proceedings does this issue cover?","golden":"119th","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"}]},{"eval_id":"019e00a3-4654-7104-90ff-d36264aea63f","probe":"Who did Speaker Mike Johnson appoint as Speaker pro tempore for the day?","golden":"Nathaniel Moran","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"}]},{"eval_id":"019e00a4-39cf-73f5-a08d-bdaf6f0e9555","probe":"Which state is Mrs. Trahan from?","golden":"Massachusetts","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"}]},{"eval_id":"019e00a4-9927-7270-b177-688639d2d84a","probe":"Which state is Mr. Thompson from?","golden":"Pennsylvania","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"}]},{"eval_id":"019e00a4-d8d8-7d76-84d9-c255fd95f7cd","probe":"How many minutes is Mrs. Trahan recognized for?","golden":"5 minutes","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"}]},{"eval_id":"019e00a5-86fd-7ef3-9421-534e8a66b6ef","probe":"How many 'yeas' were there in Roll No. 20?","golden":"214","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"}]},{"eval_id":"019e00a5-ff31-72d6-b137-910bed3336e6","probe":"How many representatives were 'not voting' in Roll No. 20?","golden":"15","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"}]},{"eval_id":"019e00a6-329c-73a0-9a01-cd95583196e9","probe":"How many 'nays' were there in Roll No. 20?","golden":"204","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"}]},{"eval_id":"019e00a7-701e-7774-bdaa-4a60fe45e545","probe":"What is the page number shown at the top left?","golden":"H276","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"}]},{"eval_id":"019e00a7-fb7c-797d-8520-954d5503a748","probe":"What is the Roll number for the vote shown on this page?","golden":"20","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"}]},{"eval_id":"019e00ac-04dd-7f1d-bcec-9be7f5c1f3ce","probe":"Did Aderholt vote yea or nay?","golden":"yea","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"}]},{"eval_id":"019e00ac-a893-7e85-9fc2-0de0e7d020dd","probe":"Did Cherfilus-McCormick vote yea or nay?","golden":"nay","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"}]},{"eval_id":"019e00ad-32af-76df-9057-a199ce91dd17","probe":"How many \"Garcia\" members are listed in the NAYS column?","golden":"3","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"}]},{"eval_id":"019e00ad-d3ed-7216-853a-30e02dbd1131","probe":"Who is the first name listed alphabetically in the NAYS column?","golden":"Adams","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"}]},{"eval_id":"019e00ae-10e5-7c6b-956c-c30654f0adda","probe":"What is the last name listed in the YEAS column?","golden":"Zinke","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"}]},{"eval_id":"019e00b0-cecb-7e7c-8149-7640c1dad861","probe":"Which member changed their vote from \"nay\" to \"yea\"?","golden":"Mr. Palmer","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"}]},{"eval_id":"019e00b3-c235-73fb-ba21-0118c8eadbf3","probe":"What is the page number shown in the top-left corner?","golden":"S250","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"}]},{"eval_id":"019e00b4-9c27-73de-8223-11187c914c6f","probe":"What is the date shown at the top-right of the page?","golden":"January 20, 2025","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"}]},{"eval_id":"019e00b9-b13c-7e4a-bf11-475eea29d6d3","probe":"Did Senator McConnell vote yea or nay on the final passage of S. 5?","golden":"yea","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"}]},{"eval_id":"019e00bb-59ee-702a-8cec-38e372b26db8","probe":"How many senators voted YEA on Amendment No. 8?","golden":"75","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"}]},{"eval_id":"019e00bb-a83a-79e5-808d-25352081e864","probe":"How many senators voted NAY on the final passage of S. 5?","golden":"35","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"}]},{"eval_id":"019e00bc-df61-7504-ab8f-56af050077d7","probe":"Who is being considered for Secretary of State on Executive Calendar No. 2?","golden":"Marco Rubio","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"}]},{"eval_id":"019e00bf-a471-719a-84c8-972702dced95","probe":"What dollar amount is mentioned as the threshold for financial harm to a State or its residents?","golden":"$100","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"}]},{"eval_id":"019e00c1-687b-7e30-917e-677d5c514e5a","probe":"Who asked for the yeas and nays on the vote for S. 5?","golden":"Mrs. Britt","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"}]},{"eval_id":"019e00c1-d9d4-7426-9471-e13471bf2c6f","probe":"How many nays were there on the vote on Amendment No. 8?","golden":"24","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"}]},{"eval_id":"019e00c6-1e73-73ec-8e95-413c88e39426","probe":"How much did the Wesley Hunt Victory Fund contribute on 2/3/2025?","golden":"$25,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"}]},{"eval_id":"019e00c6-5871-7da2-a93b-3aefb5c66f16","probe":"What is the page number shown at the top left?","golden":"S2714","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"}]},{"eval_id":"019e00c8-3f2a-7e4f-b0e4-86c796356894","probe":"How much did the Connecticut Republican State Central Committee transfer on 9/27/2024?","golden":"$10,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"}]},{"eval_id":"019e00c9-4d63-7e78-a3b2-fd24f554e0db","probe":"What was the largest single contribution amount listed in the Spouse section?","golden":"$25,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"}]},{"eval_id":"019e00c9-c213-7e12-b66f-043b2559c706","probe":"Who is being nominated to be Lieutenant Commander in the Coast Guard?","golden":"John O. Mansolillo","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"}]},{"eval_id":"019e00ce-9d49-7844-bd6c-346e75c0b284","probe":"What is the bill number for the bill to direct the Secretary of the Treasury to stop minting the penny?","golden":"S. 1525","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"}]},{"eval_id":"019e0518-b40f-7b97-99f0-2cd141711ff0","probe":"What is the bill number for the bill to regulate assault weapons?","golden":"S. 1531","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"}]},{"eval_id":"019e051c-6f18-78b3-a1d7-9d8a0a2b9618","probe":"How many senators voted yea on the Driscoll nomination?","golden":"66","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"}]},{"eval_id":"019e051d-3c27-7462-be35-0be6eece26b9","probe":"How many senators were listed as NOT VOTING?","golden":"6","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"}]},{"eval_id":"019e051d-a887-715d-88bf-933cc563b087","probe":"How many nays were there in the vote?","golden":"28","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"}]},{"eval_id":"019e051e-38d3-7d68-9805-50585c912e12","probe":"How would Senator Cruz of Texas have voted if present?","golden":"yea","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"}]},{"eval_id":"019e051f-e004-7dd8-b253-949abd5846ae","probe":"Who is Jess Andrews leaving to work for, according to Senator Kennedy's tribute?","golden":"the new Senator from Ohio","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"She is becoming deputy chief of staff to the new Senator from Ohio."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"She is becoming deputy chief of staff to the new Senator from Ohio."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"She is becoming deputy chief of staff to the new Senator from Ohio."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"She is becoming deputy chief of staff to the new Senator from Ohio."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"She is becoming deputy chief of staff to the new Senator from Ohio."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"She is becoming deputy chief of staff to the new Senator from Ohio."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The new Senator from Ohio"}]},{"eval_id":"019e0520-1d4b-7483-9ed6-1c012178bbd9","probe":"How many years has Jess Andrews run Senator Kennedy's communications shop?","golden":"5 years","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"}]},{"eval_id":"019e0520-d920-72fd-9146-7ff4401c225d","probe":"Did Senator Booker vote yea or nay on the Driscoll nomination?","golden":"nay","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"}]},{"eval_id":"019e0523-07a2-7eed-a522-32a019057e4b","probe":"Under what clause and rule were sponsors added to public bills?","golden":"clause 7 of rule XII","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"}]},{"eval_id":"019e0524-2f26-7e2d-b1d6-9d9e4787d2c7","probe":"How many additional sponsors were added to H.R. 21?","golden":"8","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"}]},{"eval_id":"019e0524-a11c-7139-bf9b-71cd8bf76e24","probe":"Who was added as a sponsor to H.R. 247?","golden":"Ms. Omar","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"}]},{"eval_id":"019e0525-2888-7fab-bbe4-24c066ee419f","probe":"Who was added as a sponsor to H.R. 31?","golden":"Mr. Stauber","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"}]},{"eval_id":"019e0529-5749-7c17-9f42-70fde0a280ae","probe":"Who was added as a sponsor to H.R. 438?","golden":"Ms. Malliotakis","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"}]},{"eval_id":"019e053e-4d48-7017-b80c-96993dddb76d","probe":"How many patients were in the SOC alone group?","golden":"4,321","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"}]},{"eval_id":"019e053f-1f3f-7cd4-9bdf-bb8319b59261","probe":"What is the table number and title?","golden":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"}]},{"eval_id":"019e0540-facb-7b6a-8fd8-3f509341da68","probe":"What was the mean age of participants in the RECOVERY trial?","golden":"66 years","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"}]},{"eval_id":"019e0541-5acc-73a2-a0f0-4a8a3fd3f3d7","probe":"When was this table last updated?","golden":"February 29, 2024","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"}]},{"eval_id":"019e0542-7270-77f1-aa19-55066dadd841","probe":"How many patients were in the SOC alone group?","golden":"4,321","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"}]},{"eval_id":"019e0543-15cb-749c-890f-dc25b546fa1f","probe":"What percentage of participants had laboratory-confirmed SARS-CoV-2 infection?","golden":"89%","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"}]},{"eval_id":"019e0547-98af-7c91-aa30-6a7096eca524","probe":"What is the table number and title shown at the top of the page?","golden":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"}]},{"eval_id":"019e0547-eecc-7d07-95de-24c48450b6a5","probe":"On what date was this document downloaded according to the bottom of the page?","golden":"3/1/2024","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"}]},{"eval_id":"019e0549-117f-704c-b2ed-3771bcbf57de","probe":"What is the URL shown at the bottom of the page where this document was downloaded from?","golden":"https://www.covid19treatmentguidelines.nih.gov/","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"}]},{"eval_id":"019e054a-48f1-7ae1-8c9a-f98de9d0fa5b","probe":"What is the recommendation for patients hospitalized but not requiring supplemental oxygen who are at high risk of progressing to severe COVID-19?","golden":"Remdesivir","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"}]},{"eval_id":"019e0550-1990-7266-9919-560f19c4cee5","probe":"In the CATCO trial, what percentage of patients received corticosteroids?","golden":"87%","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"}]},{"eval_id":"019e0550-c523-7e3c-a7bb-5e58b208e5dc","probe":"In the CATCO trial, what percentage of patients were on conventional oxygen?","golden":"54%","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"}]},{"eval_id":"019e0553-86d1-71ca-b900-5bbaabb7ca45","probe":"How many randomized controlled trials were included in the pooled analysis of individual data mentioned with ACTT-1?","golden":"9","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"}]},{"eval_id":"019e0555-7910-7ed7-a44b-456f65b6a4b0","probe":"Approximately what fraction of patients in the Solidarity trial received corticosteroids?","golden":"two-thirds","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"}]},{"eval_id":"019e055a-07af-77a5-89c9-42e3d3fa137d","probe":"What is the maximum daily dose of low-dose aspirin?","golden":"81 mg","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"}]},{"eval_id":"019e055a-a680-7323-8d08-3ac187ccf89f","probe":"What is the rating for IVIG monotherapy when glucocorticoids are contraindicated?","golden":"BIIb","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"}]},{"eval_id":"019e055d-286a-7563-a7e4-fcf6471dab8b","probe":"What is the dose of infliximab listed for intensification therapy?","golden":"5\u201310 mg/kg IV for 1 dose","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"}]},{"eval_id":"019e055e-28ea-7f76-943f-b37787cd73cb","probe":"What is the IV dose range for high-dose anakinra?","golden":"5\u201310 mg/kg/day","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"}]},{"eval_id":"019e055f-16e9-7882-9aa1-55c4030f9893","probe":"According to footnote c, in which patients should infliximab NOT be used?","golden":"patients with macrophage activation syndrome","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"}]},{"eval_id":"019e055f-c91a-7e0f-9401-67c36bb17b91","probe":"According to the Key, what does CAA stand for?","golden":"coronary artery aneurysm","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"}]},{"eval_id":"019e0561-73ca-7c46-9bf0-5c643e61cde3","probe":"What does IBW stand for according to the Key?","golden":"ideal body weight","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"}]},{"eval_id":"019e05a7-e018-7ce5-b33f-396e12ec5cd7","probe":"What is the risk level for moderately or severely immunocompromised patients regardless of vaccination status?","golden":"High","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"}]},{"eval_id":"019e05a9-4840-7d85-a06e-f789e706a095","probe":"What is the risk level for patients with mild asthma, overweight, or well-controlled diabetes?","golden":"Low","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"}]},{"eval_id":"019e05ab-8ba2-7ab7-87ce-36b3ba6a8e47","probe":"What is the risk level shown for patients with sickle cell disease or chronic kidney disease?","golden":"Intermediate","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"}]},{"eval_id":"019e05b0-6eee-79fe-9c1a-85e69f5d1b78","probe":"What is the page number?","golden":"174","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"}]},{"eval_id":"019e05b0-9f88-7493-8093-1faf321a65c1","probe":"What is the date the document was downloaded?","golden":"3/1/2024","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"}]},{"eval_id":"019e05b0-d9cd-707e-a8fc-05816b33e002","probe":"What is the title of this section shown in the orange header?","golden":"Summary Recommendations, continued","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"}]},{"eval_id":"019e05b1-edb1-71fd-a8f1-178c8ce2372a","probe":"How many hours per day of prone ventilation does the Panel recommend?","golden":"12 to 16 hours","png_sha":"f2687af1be946044a236b7f11f8cf6f728ef1c4e9e442378d2a6ad846b6a54e4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"}]},{"eval_id":"019e05ba-b872-7e8f-9ab0-ebf540496835","probe":"How many people were in the placebo group?","golden":"761","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"}]},{"eval_id":"019e05bd-b79d-79ce-83a2-61bee82f41bd","probe":"What was the mean age of participants?","golden":"58 years","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"}]},{"eval_id":"019e05bd-fce1-7c37-9985-6a2be13c70b5","probe":"What percentage of participants received corticosteroids?","golden":"79%","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"}]},{"eval_id":"019e05bf-8d4e-7984-b130-f857ef177151","probe":"What is Pablo Tebas's financial disclosure relationship with Shionogi?","golden":"Consultant","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"}]},{"eval_id":"019e05c0-2875-7f53-8cd2-1afd5c604eef","probe":"What is Andrew T. Pavia's relationship with Haleon?","golden":"Honoraria","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"}]},{"eval_id":"019e05c1-9d7a-7ef6-8d4a-75d9a4d8bc53","probe":"What is Grant Schulert's financial disclosure relationship with Boehringer Ingelheim?","golden":"Consultant","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"}]},{"eval_id":"019e05c2-9694-7119-b6c6-e2863ab93d51","probe":"What company is Phyllis Tien disclosed as receiving research support from?","golden":"Merck","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"}]},{"eval_id":"019e05c3-4ee4-7de9-abf1-e04c45c9b57f","probe":"What is Susan Swindells's financial disclosure relationship with GSK/ViiV Healthcare?","golden":"Research support","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"}]},{"eval_id":"019e05e7-8068-7743-a656-13b1d4d4190b","probe":"How many chapter objectives are listed on this page?","golden":"5","png_sha":"4fb66d797829b4efe7d38ed6d367871d6664885f70ef83a42d3f0dfec31552e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e05e7-ce2c-772c-8efd-a4776364273c","probe":"What is the figure number for the blood pressure image?","golden":"Figure 1.0","png_sha":"4fb66d797829b4efe7d38ed6d367871d6664885f70ef83a42d3f0dfec31552e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"}]},{"eval_id":"019e05f2-f42c-7018-ab71-30b51adf12e2","probe":"What is the name of the region located between the right and left lumbar regions?","golden":"Umbilical region","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"}]},{"eval_id":"019e05f3-f4bd-74db-9544-35cd14788275","probe":"What is the name of the region directly above the umbilical region?","golden":"Epigastric region","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"}]},{"eval_id":"019e05f6-e2c6-7b53-b37c-1808bd28b0d4","probe":"What organ is shown as the example at the Organ level in the pyramid?","golden":"Bladder","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"}]},{"eval_id":"019e05f7-dd30-7195-830e-cd261e20c2b7","probe":"What organ system is shown as the example at the Organ system level?","golden":"Urinary tract system","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"}]},{"eval_id":"019e05f9-174d-779b-8451-840365bb3ab1","probe":"What type of muscle cell is shown at the Cellular level in the pyramid?","golden":"Smooth muscle cell","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"}]},{"eval_id":"019e05fa-5cd7-7bf5-ad75-0aa2f060da1e","probe":"What is the name of the plane shown at the bottom of the figure, near the body's feet?","golden":"Oblique plane","png_sha":"d0de1bb560e9b722942304e532a14882201f7692dbe44333b38e37a146f08834","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"}]},{"eval_id":"019e0a70-2afd-7288-98b1-ce3d3fbfaa95","probe":"What percentage of the human body is calcium?","golden":"1.5%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"}]},{"eval_id":"019e0a71-d77a-7463-8c88-e70ccbeb93a7","probe":"How many electrons are shown in the cloud of negative charge?","golden":"2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"}]},{"eval_id":"019e0a77-521b-7c1e-96e5-0fcfd2acccfb","probe":"How many positive charges are shown in the nucleus of the electron cloud model?","golden":"2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"}]},{"eval_id":"019e0a78-60c3-7ff1-a58d-36cf79d83532","probe":"What is the pH of blood?","golden":"7.4","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"}]},{"eval_id":"019e0a78-c1e6-7be1-b2ed-7370055ce7a4","probe":"What is the pH of baking soda?","golden":"9.5","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"}]},{"eval_id":"019e0a79-38e3-7203-9d9c-b65c2c843999","probe":"What is the pH of black coffee?","golden":"5","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e0a7f-36c1-76f1-9b7d-a75d3f8b57bc","probe":"What are the regions of the enzyme called where substrates bind?","golden":"Active sites","png_sha":"56f42b1466f0ba4fd23da4bdafef8224d214d10ff10aa671d80ddc4389ea94dd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active sites"}]},{"eval_id":"019e0a7f-f372-7caa-bdd1-9371e7bc0c6a","probe":"How many chromosomes does the page say are inside the nucleus of each cell?","golden":"46","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"}]},{"eval_id":"019e0a80-2d48-78ae-9837-df877d92d50a","probe":"Approximately how many genes do humans have in their DNA according to this page?","golden":"22,000","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Almost 22,000"}]},{"eval_id":"019e0a80-c197-7fce-a219-ddb90e59c15f","probe":"What color represents Guanine in the diagram?","golden":"Blue","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"}]},{"eval_id":"019e0a81-1a13-7011-bf33-0b2b8c97db32","probe":"What color represents Adenine in the diagram?","golden":"Red","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"}]},{"eval_id":"019e0a82-da2f-727f-896b-27e752c2b42b","probe":"What are the two types of fatty acids labeled in the phospholipid diagram?","golden":"Saturated fatty acid and unsaturated fatty acid","png_sha":"a2c418cbcdc6704d925ad4ffdd78dee38a58fc1ea68774d0094b65c486a66bf8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"}]},{"eval_id":"019e0a83-ca15-7698-adf8-be9e8fecc270","probe":"What is labeled as the area inside the cell in the large membrane illustration?","golden":"Intracellular","png_sha":"a2c418cbcdc6704d925ad4ffdd78dee38a58fc1ea68774d0094b65c486a66bf8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"}]},{"eval_id":"019e0a8c-68fb-7f92-a952-b3faa7d123a4","probe":"What is the chapter title shown in the header at the top of the page?","golden":"Cell Membrane","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"}]},{"eval_id":"019e0a91-1c2e-7311-b881-fc5c00ce52f9","probe":"What does the arrow at the bottom of the diagram represent?","golden":"Time","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"}]},{"eval_id":"019e0a91-e6fb-79fb-b85f-ccfa87b7f449","probe":"What is labeled above the lipid bilayer in the center of the diagram?","golden":"Extracellular fluid","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"}]},{"eval_id":"019e0a92-7404-7aab-b271-b5cbb06491b3","probe":"What is labeled below the lipid bilayer in the center of the diagram?","golden":"Cytoplasm","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"}]},{"eval_id":"019e0a94-7773-7d3d-b4db-4925da2a4c81","probe":"What are the three labels above the cell images in Figure 3.1.6?","golden":"Hypertonic, Isotonic, Hypotonic","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"}]},{"eval_id":"019e0a94-dfda-768c-897f-34618204bf19","probe":"What is labeled between the two beakers in Figure 3.1.5?","golden":"Semipermeable membrane","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"}]},{"eval_id":"019e0aa6-cdb4-70a0-951f-040144680d97","probe":"What is labeled in purple at the center of the diagram?","golden":"Crystalline core","png_sha":"29f66040d5b404ad4868b569f57abcbd771a080fa8fcc185a3187093b4d3defb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"}]},{"eval_id":"019e0ab1-a72f-70b0-9619-a8e2a81fee46","probe":"What are the four nitrogenous bases listed in the legend?","golden":"Adenine, Thymine, Guanine, Cytosine","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"}]},{"eval_id":"019e0ab3-3b2c-7cf7-9e5a-87076b99eb2f","probe":"What color is used to represent Guanine in the legend?","golden":"Blue","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"}]},{"eval_id":"019e0ab4-5e27-7fa0-bdb3-55833bf40f16","probe":"What type of bonds connect the two DNA strands together according to the diagram?","golden":"Hydrogen bonds","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"}]},{"eval_id":"019e0ac7-674b-7f8f-ac85-ce02731c302a","probe":"How many stages are shown in the diagram at the top of the page?","golden":"6","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"}]},{"eval_id":"019e0ac8-36ba-7365-9435-ec92bf202c05","probe":"According to figure 3.5.3, what is the first phase of mitosis?","golden":"Prophase","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"}]},{"eval_id":"019e0ac9-ab1a-7551-88fe-ba669d0ab987","probe":"What is the last stage shown in the cell division diagram (after telophase)?","golden":"Cytokinesis","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"}]},{"eval_id":"019e0ad3-52d5-7f4c-8d3d-591d2476cefd","probe":"What is at the very top of the stem cell differentiation diagram?","golden":"Totipotent embryonic stem cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"}]},{"eval_id":"019e0adb-d424-739a-88c3-a9c6837b69aa","probe":"What type of stem cell is at the top of the diagram?","golden":"Totipotent embryonic stem cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"}]},{"eval_id":"019e0ae7-f32b-7670-af77-ced5432c5f69","probe":"What specialized cell type is shown between 'Heart muscle' and 'Skin' in the bottom row?","golden":"Red blood cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"}]},{"eval_id":"019e0b0b-0842-7562-aaee-a34590209d11","probe":"What is the figure title for Figure 4.6.2?","golden":"Development of Cancer","png_sha":"c97dbfb9dac36762398856cdab61d5779eae44284b94b744c8e56704bbf954e8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"}]},{"eval_id":"019e0b18-8c5a-7124-bb30-6bd93445411f","probe":"What does the label point to in the middle diagram?","golden":"Cell division accelerates","png_sha":"c97dbfb9dac36762398856cdab61d5779eae44284b94b744c8e56704bbf954e8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"}]},{"eval_id":"019e0b35-2b57-7c4e-9af5-fa094b59bb2c","probe":"What cell type is shown in the bottom-right image of the diagram?","golden":"Pancreatic cell","png_sha":"7b24760285552c0a3e2beb4a713373cf7079657b1996b630c4cab49bb81d2a0c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"}]},{"eval_id":"019e0eaf-c1cd-797e-834b-863d872f236e","probe":"What cell type is shown in the bottom-left image of the diagram?","golden":"Lung cell","png_sha":"7b24760285552c0a3e2beb4a713373cf7079657b1996b630c4cab49bb81d2a0c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"}]},{"eval_id":"019e0eb0-b4d4-72a3-99bd-8214864274dd","probe":"Which long bone is shown as the example in the diagram?","golden":"Femur","png_sha":"649d7b93ee3bd97ec82fa0d6dc7eb1ef1d3a531661aaf8e5a64a2e776e7befdf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"}]},{"eval_id":"019e0eb5-35af-7967-8d48-00aa0aa1a645","probe":"According to table 11.4, what is the origin of the superior oblique?","golden":"Sphenoid bone","png_sha":"e52a483f3e3402fc6874a991f546b566e2a6a0e32ba17df2ef455c46bc8e0793","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"}]},{"eval_id":"019e0eb7-fc68-7c2e-ad2c-3675d09c8aa1","probe":"What color represents the appendicular skeleton in the diagram's key?","golden":"Purple","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue (lavender)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue (lavender)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue (lavender)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue (lavender)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue (light purple)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue (lavender)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue (lavender)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue (lavender)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue (lavender)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple (blue-purple)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple/blue (lavender)"}]},{"eval_id":"019e0eb9-5156-79fe-85f7-13b631e40c4d","probe":"What is the bone labeled between the Tibia and the Tarsals on the lower leg?","golden":"Fibula","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"}]},{"eval_id":"019e0eb9-c545-743f-b1c1-6053776f3ffb","probe":"What bone is labeled directly below the Humerus on the arm?","golden":"Ulna","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"}]},{"eval_id":"019e0eba-022c-7bba-8967-31ab884feb4d","probe":"What is the bone labeled directly below the Femur in the diagram?","golden":"Patella","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"}]},{"eval_id":"019e0eba-8701-7de9-8ba9-578294d6b194","probe":"What is the bone labeled directly between the Clavicle and the Thoracic cage?","golden":"Scapula","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"}]},{"eval_id":"019e0ebb-0d43-793d-85f7-7b2ed1575cdf","probe":"What is the bone labeled directly below the Radius on the arm?","golden":"Carpals","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"}]},{"eval_id":"019e0ebd-9465-739b-8454-3efaee4d4310","probe":"What is the label directly below 'Rotator brevis' in the Deep spinal muscles diagram?","golden":"Rotator longus","png_sha":"8267a338f131676cd4f156eb0c4a18c6d48352ad7a386fd12707e7503673af3f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"}]},{"eval_id":"019e0ebf-4889-76bf-9d21-fdeaa9903ac1","probe":"On the left hand side of the left lateral view, what muscle is labeled directly above the Anterior scalene?","golden":"Medial scalene","png_sha":"8267a338f131676cd4f156eb0c4a18c6d48352ad7a386fd12707e7503673af3f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"}]},{"eval_id":"019e0ec1-bc36-7c2e-a816-0d61d873fe40","probe":"What file name is shown in the WebScope micrograph?","golden":"054 - Peripheral nerve_001.svs","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"}]},{"eval_id":"019e0ec6-5ccb-7a48-a454-ea039c311db0","probe":"In the leftmost (first) stage of figure (a), what two structures are labeled?","golden":"Nucleus and Axon","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"}]},{"eval_id":"019e0ec7-9679-765e-943c-61c133fe490f","probe":"Which structure label appears in the rightmost (third) stage of figure (a)?","golden":"Node of Ranvier","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"}]},{"eval_id":"019e0eca-119a-763f-ac56-f38e33c22003","probe":"What four carpal bones are labeled in the figure 8.2.5?","golden":"Hamate, Trapezoid, Trapezium, Capitate","png_sha":"306e13b6e12dfea3dcc83ac66671b7f4f26e03a8658a38703694470c4b84acff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"}]},{"eval_id":"019e0ecc-c17a-7df3-a1f4-407930ed7366","probe":"How many distinct structures are labeled with leader lines on this figure?","golden":"5","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** 5\n\n**"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"**5**"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e0ecd-0967-77f3-a1b2-140685a06b07","probe":"What structure is labeled at the very top of the cell?","golden":"Microvilli","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"}]},{"eval_id":"019e0ecd-62a5-7179-841c-8e4ba5c98a0a","probe":"What structure is labeled at the very bottom of the cell?","golden":"Nucleus","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"}]},{"eval_id":"019e0ece-41ab-74ba-b577-6e0aff6ee57c","probe":"What labeled structure appears between the Rough ER and the Nucleus?","golden":"Golgi apparatus","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"}]},{"eval_id":"019e0ece-aeb7-7000-b806-b1e7d144e6f6","probe":"What color is used to depict the Golgi apparatus in this figure?","golden":"orange","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/red"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange/pink"}]},{"eval_id":"019e0ed1-c40b-7515-aa9e-86ffff7a7b0a","probe":"In figure (a), labeled \"Loosely held,\" what object is being held?","golden":"a pencil","png_sha":"294a4958d5ff0d4328b9ea9e75f13bb4f7ef1d09ee59316db09945f970fa281f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"}]},{"eval_id":"019e0ed6-4075-7e2a-8d36-a54c01ef1f0a","probe":"According to the labels in the figure, which Roman numeral is assigned to the Olfactory nerve?","golden":"I","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"}]},{"eval_id":"019e0ed6-d0db-7047-a35c-28a5f0394d4e","probe":"How many cranial nerves are labeled in this figure?","golden":"12","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"}]},{"eval_id":"019e0ed7-29c1-7353-a0d0-78dc86f5bf0d","probe":"Which cranial nerve is labeled with the Roman numeral X?","golden":"Vagus nerve","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"}]},{"eval_id":"019e0ed7-a580-70c5-9af2-82e1e6d3b27c","probe":"Which cranial nerve is labeled directly above the Trochlear nerve on the left side of the figure?","golden":"Oculomotor nerve","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"}]},{"eval_id":"019e0ed8-e384-740f-8339-b731e7477bd0","probe":"Which Roman numeral is assigned to the Trigeminal nerve?","golden":"V","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"}]},{"eval_id":"019e0ee0-04e8-7f4f-a3d3-f732f8ce4367","probe":"What does the x-axis represent?","golden":"Time","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"}]},{"eval_id":"019e0ee2-00eb-788b-982a-17e9bbe92888","probe":"How many separate cross-section illustrations are shown in Figure 14.1.1","golden":"3","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"}]},{"eval_id":"019e0ee4-1b7c-773f-963c-fc9c8846cdc2","probe":"In the rightmost (third) illustration of Figure 14.1.1, what label appears at the far right?","golden":"Ectoderm","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"}]},{"eval_id":"019e0ee5-7413-77ac-928e-9349a0add2e3","probe":"In the far-left illustration of Figure 14.1.1, what word is labeled at the end of the curved arrow?","golden":"Convergence","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"}]},{"eval_id":"019e0ee7-d44b-7f7f-9dde-44db50c5a6d7","probe":"In panel (a), what label is shown at the top-left of the panel?","golden":"Resting muscle","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"}]},{"eval_id":"019e0ee8-b795-7df0-985e-b6a23bc84e11","probe":"In panel (b), what process is shown at the top-right when oxygen is present?","golden":"Aerobic respiration","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"}]},{"eval_id":"019e0ee9-027b-7c34-9c19-e3a9f92ddc36","probe":"In panel (b), what is produced when there is no oxygen?","golden":"Lactic acid","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"}]},{"eval_id":"019e0eea-1322-709e-b1c1-430100607e7d","probe":"In panel (c), what four products come OUT of cellular respiration?","golden":"ATP, Heat, CO\u2082, H\u2082O","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"}]},{"eval_id":"019e0eee-1192-75e7-bc00-9eba77492379","probe":"In Figure 17.5.2, what does step 1 say?","golden":"Blood calcium concentration drops","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"}]},{"eval_id":"019e0eee-6b0f-7623-9bf9-f65dcda769bd","probe":"In Figure 17.5.2, what does step 4 say?","golden":"Blood calcium levels increase","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"}]},{"eval_id":"019e0ef0-10bf-71af-9ca6-cd2d668f1d1c","probe":"In Figure 17.5.2, what does step 6 describe the effects of?","golden":"calcitonin on bone","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Calcitonin on bone"}]},{"eval_id":"019e0ef1-0b05-7277-bad0-8b16372f30ef","probe":"In Figure 17.5.2, what is the title of item 3b?","golden":"Effects of PTH on kidneys","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"}]}]},{"summary":{"model":"gpt_5_5","name":"GPT-5.5","total_evals":550,"total_cells":16500,"l2_cells":15204,"l3_cells":939,"l4_cells":357,"acceptable":97.84,"runs":30,"partial":false,"l2_evals":481,"l3_evals":43,"l4_evals":26},"evals":[{"eval_id":"019dfafb-dcbb-70a3-96b4-fcb14e3ee61c","probe":"What was the cost of revenues for 2023?","golden":"$133,332 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"133,332  \n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"133,332  \n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"133,332\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"133,332\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"133,332  \n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"}]},{"eval_id":"019dfb10-c712-7d30-9f15-c857b9160151","probe":"What was the EMEA revenue for the nine months ended September 30, 2025?","golden":"$84,096 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"84,096  \n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"84,096  \n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"84,096  \n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"84,096  \n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"84,096  \n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"}]},{"eval_id":"019dfb11-2196-7673-aeb2-eebcf53e53b2","probe":"What was the APAC revenue for the three months ended September 30, 2024?","golden":"$14,547 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"14,547  \n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"14,547  \n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"14,547  \n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"14,547  \n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"14,547  \n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"}]},{"eval_id":"019dfb22-9390-7dca-91a4-198eb5ec30b4","probe":"What is the amortized cost net of ACL for Baa rated securities as of December 31, 2022?","golden":"$81,280 million","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"81,280  \n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"81,280  \n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"81,280  \n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"81,280  \n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"81,280  \n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"}]},{"eval_id":"019e007e-5b89-72a2-b531-375ac7e4ca75","probe":"What is the dollar amount of Operating Grants and Contributions?","golden":"$74.9 billion","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9  \n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9  \n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9  \n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9  \n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9  \n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"$74.9"}]},{"eval_id":"019de200-d499-74c0-a9b3-74b464fcf74b","probe":"What is the color name listed for the carpet base?","golden":"503 Ginger","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":14,"verdict":4,"source":"precedent","note":"wrong value","answer":"Ginger"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"}]},{"eval_id":"019dfafb-3912-792d-bc47-54ca00054b5c","probe":"What were the revenues for 2025?","golden":"$402,836 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"402,836  \n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"402,836  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million  \n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"402,836\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"402,836\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"402,836"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"402,836"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"402,836"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"402,836"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"402,836"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"402,836"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"402,836"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"402,836"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"402,836"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"402,836"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"402,836"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"}]},{"eval_id":"019dfafb-834e-72a8-893b-436ffbf094a2","probe":"What was the net income for 2024?","golden":"$100,118 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"100,118"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"100,118"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"100,118"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"}]},{"eval_id":"019dfafc-94fe-761b-9254-9f753ab96d14","probe":"What was the total amount of share repurchases for the nine months ended September 30, 2025?","golden":"$40,117 million","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"$40.1 billion"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"$40.1 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"$40.117 billion"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"$40.117 billion"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"$40.1 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"$40.117 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"$40.117 billion"}]},{"eval_id":"019dfb0e-aa32-78f0-b197-81311a562d15","probe":"What were the total long-lived assets in the United States as of March 31, 2025?","golden":"$149,304 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"149,304"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149,304 million"}]},{"eval_id":"019dfb0f-11dc-7143-87ab-1b18f0a0c5b8","probe":"What was Google Cloud's operating income for the three months ended March 31, 2025?","golden":"$2,177 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"2,177  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million  \n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"2,177  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million  \n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"2,177  \n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"2,177"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"2,177"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"2,177"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"2,177"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"2,177"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"2,177"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,177 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,177 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,177 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,177 million"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"2,177"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"2,177"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,177 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,177 million"}]},{"eval_id":"019dfb25-429c-7aee-a55e-43ed0574b742","probe":"What is the estimated fair value of policyholder account balances?","golden":"$115,408 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"115,408  \n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"115,408  \n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"115,408  \n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"115,408  \n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"115,408  \n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"115,408 million"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"115,408 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"115,408 million"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"115,408 million"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"115,408 million"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"115,408"}]},{"eval_id":"019dfb25-8392-72a3-af31-c1805d75def2","probe":"What is the estimated fair value of equity securities?","golden":"$1,684 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million  \n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"1,684  \n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"1,684  \n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"1,684  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"}]},{"eval_id":"019dfb26-154c-7462-80c9-ac925ac520e6","probe":"What is the notional amount of foreign currency swaps?","golden":"$56,025 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"56,025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"56,025"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"56,025"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"56,025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56,025 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"56,025"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"56,025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"56,025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"}]},{"eval_id":"019dfb45-009b-71c5-a560-66fa6f28c0b7","probe":"What were the personal income taxes for 2024?","golden":"$116.5 billion","png_sha":"be9e4b96b82c2251ae314ddc72ad643547069399fbff67cb23663b4b60410b07","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"116.5"}]},{"eval_id":"019dfffa-4c63-71d9-9bae-44bb0f5d067a","probe":"What is the total primary government amount due to component units?","golden":"$209,125","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125  \n"},{"run_index":2,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":25,"verdict":4,"source":"precedent","note":"catastrophic miss","answer":"13"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125"}]},{"eval_id":"019e000b-683c-7e54-aaf2-3d634ac03517","probe":"What is the total expenses for Education in Graph MDA-5?","golden":"$46,073 million","png_sha":"3f8e2c78a2134ddb79f740cc731c989a29e5b11d89cdb0254e1f1740d44cfdb0","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"}]},{"eval_id":"019e0081-be2e-71be-9017-964db6e9e08a","probe":"What is the maximum value shown on the map's mile scale bar?","golden":"45 Miles","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"50 Miles  \n"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"50  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles  \n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"60 Miles\n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"60 Miles\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":6,"verdict":4,"source":"precedent","note":"wrong value","answer":"60 Miles"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":11,"verdict":4,"source":"precedent","note":"wrong value","answer":"60 Miles"},{"run_index":12,"verdict":4,"source":"precedent","note":"wrong value","answer":"60 Miles"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"60"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"50 Miles"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":16,"verdict":4,"source":"precedent","note":"wrong value","answer":"60 Miles"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 miles"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"50"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"50 Miles"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"45 Miles"},{"run_index":29,"verdict":4,"source":"precedent","note":"wrong value","answer":"60 miles"}]},{"eval_id":"019e0081-ed0a-7c3a-a9ba-53b6b5920008","probe":"What word is shown as a watermark across the map?","golden":"DRAFT","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Draft  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"SAMPLE"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Draft"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"}]},{"eval_id":"019e0082-3d98-723b-b6b4-132e744dab15","probe":"Which county is labeled at the bottom-right area of the map, below Ellis?","golden":"Navarro","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Johnson\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAVARRO\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAVARRO  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Collin"},{"run_index":9,"verdict":4,"source":"precedent","note":"wrong value","answer":"Johnson"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Rooks"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":12,"verdict":4,"source":"precedent","note":"wrong value","answer":"Johnson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAVARRO"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Comanche"},{"run_index":18,"verdict":4,"source":"precedent","note":"wrong value","answer":"Johnson"},{"run_index":19,"verdict":4,"source":"precedent","note":"wrong value","answer":"Johnson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAVARRO"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAVARRO"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Hood"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":26,"verdict":4,"source":"precedent","note":"wrong value","answer":"Johnson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":29,"verdict":4,"source":"precedent","note":"wrong value","answer":"Johnson"}]},{"eval_id":"019e00ac-faaf-7e38-b571-92ff92b76932","probe":"Garcia of California voted in which column?","golden":"NAYS","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nays  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nays  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nays\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":8,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":10,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nays"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nays"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nays"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nays"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nays"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nays"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nays"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nays"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"}]},{"eval_id":"019e00ae-10e5-7c6b-956c-c30654f0adda","probe":"What is the last name listed in the YEAS column?","golden":"Zinke","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Wilson (FL)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Wilson (FL)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"}]},{"eval_id":"019e0524-2f26-7e2d-b1d6-9d9e4787d2c7","probe":"How many additional sponsors were added to H.R. 21?","golden":"8","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"6  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"7\n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"7\n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"7\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":6,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":7,"verdict":4,"source":"precedent","note":"wrong count","answer":"9"},{"run_index":8,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":9,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":12,"verdict":4,"source":"precedent","note":"wrong count","answer":"9"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":15,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":16,"verdict":4,"source":"precedent","note":"wrong count","answer":"9"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":18,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":19,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":20,"verdict":4,"source":"precedent","note":"wrong count","answer":"9"},{"run_index":21,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":23,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":24,"verdict":4,"source":"precedent","note":"wrong count","answer":"9"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":26,"verdict":4,"source":"precedent","note":"wrong count","answer":"9"},{"run_index":27,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":28,"verdict":4,"source":"precedent","note":"wrong count","answer":"7"},{"run_index":29,"verdict":4,"source":"precedent","note":"wrong count","answer":"9"}]},{"eval_id":"019e0529-025b-7daa-a5e9-a453809b33ba","probe":"How many sponsors were added to H. Res. 23?","golden":"15","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":1,"verdict":4,"source":"human","note":"wrong count","answer":"16\n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"16\n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"18\n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"17\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"wrong count","answer":"13"},{"run_index":6,"verdict":4,"source":"human","note":"wrong count","answer":"19"},{"run_index":7,"verdict":4,"source":"human","note":"wrong count","answer":"17"},{"run_index":8,"verdict":4,"source":"precedent","note":"wrong count","answer":"16"},{"run_index":9,"verdict":4,"source":"human","note":"wrong count","answer":"17"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":12,"verdict":4,"source":"precedent","note":"wrong count","answer":"16"},{"run_index":13,"verdict":4,"source":"human","note":"wrong count","answer":"17"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":15,"verdict":4,"source":"human","note":"wrong count","answer":"17"},{"run_index":16,"verdict":4,"source":"precedent","note":"wrong count","answer":"18"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":18,"verdict":4,"source":"human","note":"wrong count","answer":"19"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":20,"verdict":4,"source":"precedent","note":"wrong count","answer":"16"},{"run_index":21,"verdict":4,"source":"precedent","note":"wrong count","answer":"16"},{"run_index":22,"verdict":4,"source":"precedent","note":"wrong count","answer":"16"},{"run_index":23,"verdict":4,"source":"precedent","note":"wrong count","answer":"18"},{"run_index":24,"verdict":4,"source":"precedent","note":"wrong count","answer":"16"},{"run_index":25,"verdict":4,"source":"human","note":"wrong count","answer":"17"},{"run_index":26,"verdict":4,"source":"precedent","note":"wrong count","answer":"18"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":28,"verdict":4,"source":"precedent","note":"wrong count","answer":"16"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"}]},{"eval_id":"019e0ec1-bc36-7c2e-a816-0d61d873fe40","probe":"What file name is shown in the WebScope micrograph?","golden":"054 - Peripheral nerve_001.svs","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs  \n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs  \n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve 001.svs"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"}]},{"eval_id":"019e0ecc-c17a-7df3-a1f4-407930ed7366","probe":"How many distinct structures are labeled with leader lines on this figure?","golden":"5","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"6\n"},{"run_index":1,"verdict":4,"source":"human","note":"wrong count","answer":"6  \n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"6\n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"6  \n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"6  \n"},{"run_index":5,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":6,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":7,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":8,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":9,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":10,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":11,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":12,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":13,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":14,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":15,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":16,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":17,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":18,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":19,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":20,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":21,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":22,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":23,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":28,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"},{"run_index":29,"verdict":4,"source":"precedent","note":"wrong count","answer":"6"}]},{"eval_id":"019de200-d4b1-72c3-a2c1-2ee5369782dd","probe":"What is the title of Section 31?","golden":"Broker's Commissions","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions  \n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"}]},{"eval_id":"019de200-d4ba-7ebb-acf4-de78451b07c1","probe":"How many miles is mentioned for relocation of the Executive's principal place of employment?","golden":"25 miles","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles\n"},{"run_index":1,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles\n"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles\n"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles\n"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":6,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":7,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":8,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":9,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":10,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":11,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":12,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":13,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":14,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":15,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":16,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":17,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":18,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":19,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":20,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":21,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":22,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":23,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":24,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":25,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":26,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":27,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":28,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":29,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"twenty five (25) miles"}]},{"eval_id":"019de200-d4cb-70dc-a225-ac7807b5a70c","probe":"What is the title of Article 33?","golden":"Costs and Attorneys' Fees","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees  \n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees  \n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"}]},{"eval_id":"019de200-d507-733d-8d8c-87040ba6130c","probe":"How many days does Landlord have to give Tenant a termination notice after submission of the statement?","golden":"30 days","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days  \n"},{"run_index":1,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days  \n"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days  \n"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days  \n"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":6,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":7,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":8,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":9,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":10,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":11,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":12,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":13,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":14,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":15,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":16,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":17,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":18,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":19,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":20,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":21,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":22,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":23,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":24,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":25,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":26,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":27,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":28,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":29,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"thirty (30) days"}]},{"eval_id":"019e0085-cd0d-7043-93eb-a33714bb645a","probe":"What GASB Statement number did the Council adopt in fiscal year 2024?","golden":"No. 96","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96  \n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96  \n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96  \n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"}]},{"eval_id":"019e00a7-39d7-723b-9490-eca9ac160ad7","probe":"What time did the House reconvene after recess?","golden":"1:30 p.m.","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m.\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m.\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m.\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m.\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m.\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":6,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":7,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":8,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":9,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":10,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":11,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":12,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":13,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":14,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":15,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":16,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":17,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":18,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":19,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":20,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":21,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":22,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":23,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":24,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":25,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":26,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":27,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":28,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":29,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."}]},{"eval_id":"019e00ad-aa7b-733c-8e2b-33b7f30d7cfc","probe":"Did Senator Whittaker appear on this vote?","golden":"No, Whittaker is not listed on this page","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":6,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":7,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":8,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":9,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":10,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":11,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":12,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":13,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":14,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":15,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":16,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":17,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":18,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":19,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":20,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":21,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":22,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":23,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":24,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":25,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":26,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":27,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":28,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":29,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"}]},{"eval_id":"019e00af-5886-7c0c-acb0-3467635835d6","probe":"What time did the recorded vote take place (the \u25a1 time stamp before the McGOVERN demand)?","golden":"1:56 PM (1356)","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"1356  \n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"1356  \n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"1356  \n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"}]},{"eval_id":"019e00af-a493-76fe-9fc1-0e6baa42ab53","probe":"What time did the House return from recess (the \u25a1 time stamp before \"AFTER RECESS\")?","golden":"1:30 PM (1330)","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"}]},{"eval_id":"019e00b0-60e7-7eb0-ace3-4de6646279c2","probe":"Which members changed their vote from \"yea\" to \"nay\"?","golden":"Ms. Ross, Mrs. Foushee, Mr. Raskin, and Mr. Krishnamoorthi","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi  \n"},{"run_index":1,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi\n"},{"run_index":2,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi\n"},{"run_index":3,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi\n"},{"run_index":4,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":6,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":7,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":8,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":9,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":10,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":11,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":12,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":13,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":14,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":15,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":16,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":17,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":18,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":19,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":20,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":21,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":22,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":23,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":24,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":25,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":26,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":27,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":28,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"},{"run_index":29,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi"}]},{"eval_id":"019e051b-f048-7557-907e-87bf1f5319e0","probe":"What was the rollcall vote number for the Driscoll nomination?","golden":"Rollcall Vote No. 90 Ex.","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90 Ex.\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90 Ex.\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90 Ex.\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90 Ex.\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90 Ex.\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."}]},{"eval_id":"019e054b-b654-74aa-b2b0-ad19e229a916","probe":"What is the preferred alternative immunomodulator listed for hospitalized patients requiring HFNC oxygen or NIV?","golden":"IV tocilizumab (Blla)","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab  \n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)  \n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)  \n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"}]},{"eval_id":"019e05ac-b930-79c4-93f6-be96e504477e","probe":"Within how many months of a recent SARS-CoV-2 infection may substantial immunity be conferred, according to footnote b?","golden":"3-6 months","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months  \n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months  \n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months  \n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"}]},{"eval_id":"019e0a6f-0c3e-7520-884b-307d309c1b4b","probe":"What percentage of the human body is oxygen?","golden":"65.0%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0  \n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0  \n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0  \n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0  \n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"}]},{"eval_id":"019e0a70-2afd-7288-98b1-ce3d3fbfaa95","probe":"What percentage of the human body is calcium?","golden":"1.5%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5  \n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5  \n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5  \n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5  \n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"}]},{"eval_id":"019e0a70-8117-7662-8777-c2511bc6f2ee","probe":"What percentage of the human body is phosphorus?","golden":"1.0%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0  \n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0  \n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0  \n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"}]},{"eval_id":"019e0a76-b33e-7648-8be4-ced32e601bf5","probe":"What element is shown in the planetary model?","golden":"Helium (He)","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"helium  \n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"helium  \n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium  \n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"helium  \n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"helium  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":8,"verdict":3,"source":"human","note":"answer compressed","answer":"He"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":18,"verdict":3,"source":"human","note":"answer compressed","answer":"He"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"Helium"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":26,"verdict":3,"source":"human","note":"answer compressed","answer":"He"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"He"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"helium"}]},{"eval_id":"019e0a9d-62f1-726d-9b24-bbeb2b85b199","probe":"According to the caption of Figure 3.1.5, which side of the membrane (left or right) shows the hypertonic solution?","golden":"the right side","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"right  \n"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"right  \n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"right  \n"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"right  \n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"right side  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":6,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":7,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":8,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":9,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":10,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":11,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":12,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":13,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":14,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":15,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":16,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":17,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":18,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":19,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":20,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":21,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":22,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":23,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":24,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":25,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":26,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":27,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":28,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":29,"verdict":3,"source":"precedent","note":"article handling","answer":"right"}]},{"eval_id":"019e0ad4-4005-7307-aae9-78e3049f1a65","probe":"What are the three lines that pluripotent embryonic stem cells differentiate into?","golden":"Endoderm, Mesoderm, and Ectoderm","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line  \n"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line  \n"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line  \n"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line; Mesoderm line; Ectoderm line  \n"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":6,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":7,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":8,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line; Mesoderm line; Ectoderm line"},{"run_index":9,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":10,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":11,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":12,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":13,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":14,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":15,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":16,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":17,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":18,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":19,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":20,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":21,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":22,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":23,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":24,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":25,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":26,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":27,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":28,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":29,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"}]},{"eval_id":"019e0ed1-c40b-7515-aa9e-86ffff7a7b0a","probe":"In figure (a), labeled \"Loosely held,\" what object is being held?","golden":"a pencil","png_sha":"294a4958d5ff0d4328b9ea9e75f13bb4f7ef1d09ee59316db09945f970fa281f","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"pencil  \n"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"pencil  \n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"pencil  \n"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"pencil  \n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"pencil  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":6,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":7,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":8,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":9,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":10,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":11,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":12,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":13,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":14,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":15,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":16,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":17,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":18,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":19,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":20,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":21,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":22,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":23,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":24,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":25,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":26,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":27,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":28,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":29,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"}]},{"eval_id":"019e0ed2-1e72-7fe1-94ee-e4dcffb88ace","probe":"In figure (a), what body part is gripping the pencil?","golden":"a hand","png_sha":"294a4958d5ff0d4328b9ea9e75f13bb4f7ef1d09ee59316db09945f970fa281f","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"hand  \n"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"hand  \n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"hand  \n"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"hand  \n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"hand  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":6,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":7,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":8,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":9,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":10,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":11,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":12,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":13,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":14,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":15,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":16,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":17,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":18,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":19,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":20,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":21,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":22,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":23,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":24,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":25,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":26,"verdict":3,"source":"precedent","note":"article handling","answer":"Hand"},{"run_index":27,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":28,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":29,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"}]},{"eval_id":"019e0ede-f3cd-7412-8c25-2e079510e6e7","probe":"What is the unit shown on the y-axis label?","golden":"mV (millivolts)","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"mV  \n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"}]},{"eval_id":"019e0eea-ac39-7b97-941e-8c1e0a744ae3","probe":"In panel (c), what additional input enters the mitochondria from above (with a downward arrow)?","golden":"O\u2082 (oxygen)","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082  \n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"O2  \n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082  \n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"O2  \n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O2"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"}]},{"eval_id":"019de200-d496-74b2-a2cc-5c7a6982836d","probe":"What is the Tenant Notice Address suite number?","golden":"Suite 900","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"}]},{"eval_id":"019de200-d4f1-7b08-800d-39648227b1fc","probe":"How many days advance notice must Tenant give for an Acceleration Notice?","golden":"120 days","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days  \n"},{"run_index":1,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"one hundred twenty (120) days\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":6,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"one hundred twenty (120) days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":19,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"one hundred twenty (120) days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":23,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"one hundred twenty (120) days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"}]},{"eval_id":"019de200-d505-7a87-bf67-4ac7fc6b2fd3","probe":"How many days before policy expiration must original copies of policies be delivered to Landlord?","golden":"fifteen (15) days","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than fifteen (15) days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":24,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"15 days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"}]},{"eval_id":"019de778-2487-7ceb-942f-bbc9cce683b5","probe":"What is the public law number?","golden":"118-109","png_sha":"a0300e50b30b31b24996ac843a50187dca0d8e81f6c026161ae3e07159e9815a","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"118\u2013109"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":11,"verdict":3,"source":"human","note":"answer expanded","answer":"Public Law 118\u2013109"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":13,"verdict":3,"source":"human","note":"answer expanded","answer":"Public Law 118\u2013109"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"118\u2013109"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Public Law 118-109"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":22,"verdict":3,"source":"human","note":"answer expanded","answer":"Public Law 118\u2013109"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":24,"verdict":3,"source":"human","note":"answer expanded","answer":"Public Law 118\u2013109"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Public Law 118-109"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"}]},{"eval_id":"019dfb3f-d06a-7547-a4b6-8a6e4c150c61","probe":"What is the suite number of the office address listed at the bottom of the letter?","golden":"Suite 1850","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850  \n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850"}]},{"eval_id":"019dfffd-a1d4-7a49-94b8-3ef9aa5497d4","probe":"What are the two highest courts shown under the Judicial branch?","golden":"The Supreme Court of Texas and The Court of Criminal Appeals","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":8,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"The Supreme Court of Texas; The Court of Criminal Appeals"},{"run_index":9,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"The Supreme Court of Texas; The Court of Criminal Appeals"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":17,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"The Supreme Court of Texas; The Court of Criminal Appeals"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":27,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"The Supreme Court of Texas; The Court of Criminal Appeals"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"}]},{"eval_id":"019dffff-131f-7d34-8e0c-2be25da41c0d","probe":"What two courts are shown at the bottom level under County-Level Courts?","golden":"Municipal Courts and Justice of the Peace Courts","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts\n"},{"run_index":1,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts  \n"},{"run_index":2,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts\n"},{"run_index":3,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts\n"},{"run_index":4,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts\n"},{"run_index":5,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":7,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":9,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":10,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":11,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":12,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":13,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":16,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":17,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":19,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":20,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":21,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":23,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":24,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":26,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":28,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts; Justice of the Peace Courts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"}]},{"eval_id":"019e0005-d4aa-7f1f-8391-f99f6caf3697","probe":"How many City Council Members are from Brooklyn?","golden":"16 Members","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"}]},{"eval_id":"019e0006-0655-7fe4-88c4-d697fbcb759a","probe":"How many Council Members does Queens have?","golden":"14 Members","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"}]},{"eval_id":"019e003d-d1bc-7fb0-a78b-4b79600f8252","probe":"Who is the Custodian of Funds?","golden":"Brad Lander, Comptroller of the City of New York","png_sha":"89c77daf9c6f881f0116f445cbf736cffc12698b60a93b437699a1a075b00138","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander  \n"},{"run_index":1,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":6,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":7,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":10,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":13,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":16,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":17,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":18,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":20,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":23,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"}]},{"eval_id":"019e00b5-3554-76cc-805e-ff8228bfefae","probe":"What was the rollcall vote number for the vote on Amendment No. 8?","golden":"Rollcall Vote No. 6 Leg.","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg.\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"Rollcall Vote No. 6"}]},{"eval_id":"019e00b6-0ba2-731c-a9ed-436b1a7ef320","probe":"What was the rollcall vote number for the vote on S. 5?","golden":"Rollcall Vote No. 7 Leg.","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rollcall Vote No. 7  \n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7  \n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg.\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rollcall Vote No. 7  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"Rollcall Vote No. 7"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"Rollcall Vote No. 7"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"Rollcall Vote No. 7"},{"run_index":18,"verdict":3,"source":"human","note":"answer compressed","answer":"Rollcall Vote No. 7"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":22,"verdict":3,"source":"human","note":"answer compressed","answer":"Rollcall Vote No. 7"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"Rollcall Vote No. 7"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"Rollcall Vote No. 7"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"}]},{"eval_id":"019e051f-e004-7dd8-b253-949abd5846ae","probe":"Who is Jess Andrews leaving to work for, according to Senator Kennedy's tribute?","golden":"the new Senator from Ohio","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio  \n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"our new Senator from Ohio\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":6,"verdict":3,"source":"precedent","note":"article handling","answer":"our new Senator from Ohio"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":9,"verdict":3,"source":"precedent","note":"article handling","answer":"our new Senator from Ohio"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio"}]},{"eval_id":"019e05b5-b5f0-7a24-b00b-652882db4074","probe":"What plateau pressure does the Panel recommend targeting?","golden":"<30 cm H2O","png_sha":"f2687af1be946044a236b7f11f8cf6f728ef1c4e9e442378d2a6ad846b6a54e4","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O  \n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O  \n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"}]},{"eval_id":"019e05e9-158a-7e0b-a377-74df9d26138b","probe":"How many abdominal regions are shown in figure (a)?","golden":"nine","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":20,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"}]},{"eval_id":"019e05f4-56d1-7193-845a-2889286704f6","probe":"How many abdominal quadrants are shown in figure (b)?","golden":"four","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":29,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"}]},{"eval_id":"019e0a77-09dc-7990-a971-9e556b040d8c","probe":"What symbol is used to label the electron in the planetary model?","golden":"e\u2212","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212  \n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212  \n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"e\u2212"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"}]},{"eval_id":"019e0a9e-aa0f-7a55-89e3-a0cd7f73e21f","probe":"What chemical formula is shown next to each red blood cell in the bottom row of Figure 3.1.6?","golden":"H2O","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O  \n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O  \n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O  \n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"}]},{"eval_id":"019e0ac6-e7e3-7800-ac52-eee064e4e8b7","probe":"What is the scale bar length shown in the microscope images?","golden":"5 \u03bcm","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m  \n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m  \n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm  \n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"5 \u00b5m"}]},{"eval_id":"019e0eea-1322-709e-b1c1-430100607e7d","probe":"In panel (c), what four products come OUT of cellular respiration?","golden":"ATP, Heat, CO\u2082, H\u2082O","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O  \n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, heat, CO2, H2O  \n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, heat, CO2, H2O  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O  \n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, heat, CO2, H2O  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, heat, CO2, H2O"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, heat, CO2, H2O"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, heat, CO2, H2O"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, heat, CO2, H2O"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, heat, CO2, H2O"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, heat, CO2, H2O"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, heat, CO2, H2O"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, heat, CO2, H2O"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, heat, CO2, H2O"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, heat, CO2, H2O"}]},{"eval_id":"019de200-d48b-7a0c-9e79-d846c27a96b5","probe":"What page does Article XI Security Deposit start on?","golden":"50","png_sha":"625ba89847b64383ae07efde4a0b7374c88fd2b6dcff552df6812dad32d03160","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"}]},{"eval_id":"019de200-d48c-70ff-b28a-a9c240e3486b","probe":"Who is the landlord named on this office lease?","golden":"Lanham Office 2015 LLC","png_sha":"625ba89847b64383ae07efde4a0b7374c88fd2b6dcff552df6812dad32d03160","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"}]},{"eval_id":"019de200-d48d-703c-b522-b34424519003","probe":"What is Exhibit L?","golden":"Competitor List","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"}]},{"eval_id":"019de200-d48e-767a-b928-9b2d12086653","probe":"What is Exhibit H?","golden":"Roof Access Agreement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"}]},{"eval_id":"019de200-d48f-7596-abf5-cacd23054c4d","probe":"What is Exhibit J?","golden":"Parking Easement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"}]},{"eval_id":"019de200-d490-71ff-a39d-ee962a11796e","probe":"What is Exhibit D?","golden":"Certificate Affirming the Must Take Commencement Date","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"}]},{"eval_id":"019de200-d491-71d6-875d-4fa564623978","probe":"What is Exhibit B?","golden":"Work Agreement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"}]},{"eval_id":"019de200-d492-726b-87fc-5718790d5ebd","probe":"What is Exhibit E?","golden":"Measurement Schedule","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"}]},{"eval_id":"019de200-d493-74c3-af46-0469929cc88d","probe":"What is the Tenant Notice Address?","golden":"8201 Corporate Drive, Suite 900, Landover, MD 20785","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer; thereafter, the Premises, Attention: Chief Financial Officer; with a copy to: General Counsel."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer; thereafter, the Premises, Attention: Chief Financial Officer, with a copy to General Counsel."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer; thereafter, the Premises, Attention: Chief Financial Officer. With a copy to: General Counsel."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"}]},{"eval_id":"019de200-d494-73d8-930e-be33d26373fa","probe":"What section is referenced for the definition of 'Tax Benefits'?","golden":"Section 5.6","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"}]},{"eval_id":"019de200-d495-7bf0-9c87-96d57c098e71","probe":"What section is referenced for the definition of 'Threshold Successors'?","golden":"Section 10.1","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1."}]},{"eval_id":"019de200-d497-758c-9ad2-fceee7efd1fa","probe":"What section is referenced for the definition of 'Tenant's Plans'?","golden":"Section 9.4(a)","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"}]},{"eval_id":"019de200-d498-741d-b3e0-3374c9b02dfc","probe":"What is the title of section H?","golden":"Tenant Modular Furniture","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"}]},{"eval_id":"019de200-d49a-7b22-8b95-3fe120b21efc","probe":"What is the section number for the CARPET section?","golden":"09680","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"}]},{"eval_id":"019de200-d49b-76ae-aecb-69e6ba967a73","probe":"What is the section number for the PAINTING section?","golden":"09900","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"}]},{"eval_id":"019de200-d49c-75ca-963f-0649d0c70719","probe":"What is the section number for ACOUSTICAL CEILING?","golden":"09510","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"}]},{"eval_id":"019de200-d49d-7cee-91a2-4ed07626e90a","probe":"What is the name of the company shown in the schedule heading on this page?","golden":"Acadia Realty Trust","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"}]},{"eval_id":"019de200-d49e-7120-8c57-be2e37f1a894","probe":"What is the page number shown at the bottom of the upper section of this page?","golden":"166","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"}]},{"eval_id":"019de200-d49f-72ce-9b9d-97ba16d5640c","probe":"What is the depreciation period (useful life in years) listed in the rightmost column for every property on this page?","golden":"40 years","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"}]},{"eval_id":"019de200-d4a0-7403-856e-aa22d2bdae81","probe":"What is the name of the company shown at the top of the page?","golden":"Acceleron Pharma Inc.","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."}]},{"eval_id":"019de200-d4a1-7f82-aa55-38eac3b9b487","probe":"What is the total deferred tax assets for 2017 (in thousands)?","golden":"145,657","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"}]},{"eval_id":"019de200-d4a2-7a39-91ad-766fdf7c2010","probe":"What is the page number shown at the bottom center of the page?","golden":"F-29","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"}]},{"eval_id":"019de200-d4a3-7518-9715-cc1bb9edb084","probe":"What is the deferred revenue amount for 2016 (in thousands)?","golden":"1,666","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"}]},{"eval_id":"019de200-d4a4-7cca-a0e9-a3ce81d8b684","probe":"What is the federal income tax expense at the statutory rate for 2015?","golden":"34.0%","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"}]},{"eval_id":"019de200-d4a5-753e-87a5-2c51cb711be4","probe":"What is the Research and development credits amount for 2017 (in thousands)?","golden":"12,548","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"}]},{"eval_id":"019de200-d4a6-72d4-b715-3cd7f42e4f66","probe":"What is the State income tax, net of federal benefit percentage for 2016?","golden":"5.9%","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"}]},{"eval_id":"019de200-d4a7-74af-afa8-d3ad189499cc","probe":"What is the deposit amount mentioned in this document?","golden":"$500,000.00","png_sha":"5a5e3841491b2b356eb9b963e45419183ebf6ffae298e69a6f9dd5488bc23e1c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"}]},{"eval_id":"019de200-d4a8-7bdc-bc00-d50a60d60dcc","probe":"What is the title of section 16?","golden":"Mutual Waiver of Subrogation Rights","png_sha":"674a83793665d045c76513a816f7fc9099c52baccd94af7ee817a5f89cdc81d5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."}]},{"eval_id":"019de200-d4a9-7107-917d-4d1e160c26b3","probe":"What is the anticipated commencement date?","golden":"March 1, 2016","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"}]},{"eval_id":"019de200-d4aa-7225-85f5-76e6b1382af9","probe":"What is the premises address?","golden":"2665 North First Street, Suite 300, San Jose, California 95134","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"}]},{"eval_id":"019de200-d4ab-727c-ae0c-07bdc5f94836","probe":"What is the tenant's trade name?","golden":"8x8, Inc.","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."}]},{"eval_id":"019de200-d4ac-742d-b65a-74bd92f2893d","probe":"What is the name of the broker listed in Section 31?","golden":"Cresa Global, Inc.","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."}]},{"eval_id":"019de200-d4ad-71b2-aae9-616c2d5fdb91","probe":"What is the title of Section 33?","golden":"Holding Over","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"}]},{"eval_id":"019de200-d4ae-7bb5-8e56-dfba0d289a6a","probe":"What is the title of Section 38?","golden":"Miscellaneous","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"}]},{"eval_id":"019de200-d4af-7ae9-9bf2-f9ad2d8f5ea5","probe":"What is the title of Section 32?","golden":"Estoppel Certificate","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"}]},{"eval_id":"019de200-d4b0-7068-9693-c265751b0823","probe":"What is the title of Section 34?","golden":"Assignment and Subletting","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"}]},{"eval_id":"019de200-d4b2-7946-80ee-a29424252d23","probe":"What is the title of section 14.3?","golden":"Transfer Premium","png_sha":"cde4659cf5512e2c7b127af66eb4bab815dcc533bb04fce540d6d56b21cbb6cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"}]},{"eval_id":"019de200-d4b3-7330-8b3a-3010528a30fa","probe":"What is the title of section 14.5?","golden":"Effect of Transfer","png_sha":"cde4659cf5512e2c7b127af66eb4bab815dcc533bb04fce540d6d56b21cbb6cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer."}]},{"eval_id":"019de200-d4b4-702e-932f-bb5b6dbb2b20","probe":"What is the title of Article XXIX?","golden":"Expansion Rights","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"}]},{"eval_id":"019de200-d4b5-709e-9897-f8440e2a964f","probe":"What is the title of Article XXX?","golden":"METROPLEX II ASSUMPTION","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex II Assumption"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex II Assumption"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"}]},{"eval_id":"019de200-d4b6-73e9-aa56-a2eb7119541a","probe":"What is the title of Section 29.1?","golden":"Right of First Refusal","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal."}]},{"eval_id":"019de200-d4b7-7604-b550-db1d11ebef12","probe":"What is the title of Section 28.2?","golden":"Additional Amenities","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"}]},{"eval_id":"019de200-d4b8-7164-91b2-3ec03d9f397f","probe":"What is the title of section 12?","golden":"Severance Payments","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"}]},{"eval_id":"019de200-d4b9-723f-8a38-4f373e93bffa","probe":"What is the title of section 13?","golden":"Certain Covenants of the Executive","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"}]},{"eval_id":"019de200-d4bb-7ca6-ada6-5158e0ca9947","probe":"What is the item number for the Foreperson/Day Porter Executive dress shirt?","golden":"#828","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"}]},{"eval_id":"019de200-d4bc-76fc-9589-06797f38e895","probe":"What is the title of section E?","golden":"UNIFORMS","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"}]},{"eval_id":"019de200-d4bd-7e20-a10a-47c622032b52","probe":"What is the item number for the women's Pleated Dress Pants?","golden":"#596","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"}]},{"eval_id":"019de200-d4be-7e4d-b5ce-bf5d0d9e3745","probe":"What is the title of section J?","golden":"LIGHTING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"}]},{"eval_id":"019de200-d4bf-7a42-91f9-d00fe759f635","probe":"What is the title of section H?","golden":"SECURITY AND INCIDENT REPORTING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"}]},{"eval_id":"019de200-d4c0-7843-8047-cc09e991e12b","probe":"What is the title of section K?","golden":"GREEN CLEANING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"}]},{"eval_id":"019de200-d4c1-76bf-b140-f4b73e70f7ed","probe":"What is the maximum sound level (in dBA) allowed for vacuum cleaners?","golden":"70dBA","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70 dBA"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"}]},{"eval_id":"019de200-d4c2-7ad3-88a8-ed0b24b345b7","probe":"What is the item number for the men's Foreperson/Day Porter Pleated dress pants?","golden":"#865","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"}]},{"eval_id":"019de200-d4c3-7771-b087-cb7f248214a4","probe":"What is the item number listed for the women's Long Sleeve Dress Blouse?","golden":"#528","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"}]},{"eval_id":"019de200-d4c4-736b-b432-833199724c46","probe":"What is the title of section 24.0?","golden":"HOLDOVER","png_sha":"214b816ecbf747322726d54a0cb92edd6d184be6a6e04656e532d637c65eda11","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"}]},{"eval_id":"019de200-d4c5-7b98-9a5a-c76d5fb5ae1e","probe":"What is the title of section 5.2?","golden":"Operating Expenses; Consumable Expenses and Base Building Expenses","png_sha":"3343506981bd41f08b63b8df40f8ba763e2bc1566a850d0903f24b1c5782cf77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."}]},{"eval_id":"019de200-d4c6-7729-866a-8ac3402457fb","probe":"What is the title of Article XIV?","golden":"Assignment and Subletting","png_sha":"d8fa233fb12db1beef1e4088d39215700d5884c2d4cb968b6985c6febde8a2ca","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"}]},{"eval_id":"019de200-d4c7-7305-82b7-76d4d75e7f9d","probe":"What is the title of Article XIII?","golden":"Condemnation","png_sha":"d8fa233fb12db1beef1e4088d39215700d5884c2d4cb968b6985c6febde8a2ca","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"}]},{"eval_id":"019de200-d4c8-787c-9ed4-e33640efb435","probe":"What is the title of Article 28?","golden":"Confidentiality","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"}]},{"eval_id":"019de200-d4c9-7b7f-9e32-c47d4f1c0b0e","probe":"What is the title of Exhibit D?","golden":"Form of Deed","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"}]},{"eval_id":"019de200-d4ca-7805-9cc9-6e26cd367bbc","probe":"What is the title of Article 25?","golden":"Waiver of Jury Trial","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"}]},{"eval_id":"019de200-d4cc-7013-9323-c4a463e49255","probe":"What is the Lessor's telephone number listed in the notices section?","golden":"(81) 8358.7978","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"}]},{"eval_id":"019de200-d4cd-7c1a-a4b1-fd5dc2875413","probe":"What is the title of section 24.4?","golden":"Captions","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"}]},{"eval_id":"019de200-d4ce-73b9-b787-b0f7568e7018","probe":"What is the Lessee's telephone number listed in the notices section?","golden":"(81) 8158.8800","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"}]},{"eval_id":"019de200-d4cf-7e95-8f4b-cca6ed5396ce","probe":"What is the title of section 24.5?","golden":"Severability","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"}]},{"eval_id":"019de200-d4d0-7008-bd98-2d410f1fb7fa","probe":"What is the name of the person to contact for the Lessor in the notices section?","golden":"Mr. Juan Carlos Gonzalez Quezada","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"}]},{"eval_id":"019de200-d4d1-7e39-92cb-dc82b006e040","probe":"What is the title of section 24.1?","golden":"Brokers","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"}]},{"eval_id":"019de200-d4d2-7ff3-ae3f-b7ce26ebedc4","probe":"What is the title of section 22.3?","golden":"Labor","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"}]},{"eval_id":"019de200-d4d3-7a72-9dfe-0011bce8efc8","probe":"What is the maximum tenant improvement allowance amount in dollars?","golden":"$559,160.00","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"}]},{"eval_id":"019de200-d4d4-7185-bf69-9197f90e27ce","probe":"What is the title of Section II?","golden":"TENANT'S WORK","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"}]},{"eval_id":"019de200-d4d5-7ac3-8e4e-c758cbae290a","probe":"What is the per square foot dollar amount mentioned for the Allowance?","golden":"$40.00","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00 per square foot  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00 per square foot"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00 per square foot"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00 per square foot"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"}]},{"eval_id":"019de200-d4d6-77e1-9296-5f9e11cf7728","probe":"What does item (c) say?","golden":"Intentionally deleted.","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."}]},{"eval_id":"019de200-d4d7-71ee-b89a-13f57933c5ed","probe":"What is the company name shown in the headers of the financial statements?","golden":"Acadia Realty Trust and Subsidiaries","png_sha":"d99abf4bae64753a77c680d1e83acdbdc08eb377e9da9bc0a4af8337f67971e2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"}]},{"eval_id":"019de200-d4d8-73df-b318-56c93e913a1d","probe":"What is the rent payable for December 2016 in the Metroplex Rent table?","golden":"137,399","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"}]},{"eval_id":"019de200-d4d9-7080-91a1-8e4024ae5b27","probe":"What is the title of Exhibit M?","golden":"Metroplex Rent","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"}]},{"eval_id":"019de200-d4da-740b-af0a-30cdbbdc3a00","probe":"What is the rent payable for July 2018?","golden":"145,763","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"}]},{"eval_id":"019de200-d4db-76f8-b9cf-eb901aaef607","probe":"What is the title of Exhibit N?","golden":"Exclusions From Operating Expenses","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"}]},{"eval_id":"019de200-d4dc-76d9-b19c-2bb2f2c2d455","probe":"What is the rent payable for March 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4dd-7a8e-97e8-6cbb97c9f288","probe":"What is the rent payable for January 2018?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4de-7510-a1bb-a2200cf532b1","probe":"What is the rent payable for May 2018?","golden":"145,763","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"}]},{"eval_id":"019de200-d4df-72db-b8e2-5470717b76c7","probe":"What is the rent payable for September 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4e0-7497-8998-04b404a57589","probe":"What is listed as item (i) under Excluded Expenses in Exhibit N?","golden":"Real Estate Taxes","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"}]},{"eval_id":"019de200-d4e1-704d-bad7-731b3da45bdf","probe":"What is the rent payable for November 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4e2-7aab-ae79-29c74e645fca","probe":"What is the title of Exhibit C?","golden":"Technology Exhibit","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"}]},{"eval_id":"019de200-d4e3-7937-8135-40c4b4f0cb8e","probe":"What is the markup percentage on outgoing mail?","golden":"10%","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"}]},{"eval_id":"019de200-d4e4-7765-86d5-d5fb371119ed","probe":"What is the title of Exhibit B?","golden":"Summit Billing Information","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"}]},{"eval_id":"019de200-d4e5-7bb2-9e8d-5d17eac142de","probe":"What is the reconnection fee per hour mentioned in Exhibit C?","golden":"$100","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"}]},{"eval_id":"019de200-d4e6-7499-90b0-274586c057d5","probe":"What are the standard business hours listed for Summit's remedial maintenance?","golden":"9:00 am to 5:00 pm, Monday - Friday","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"}]},{"eval_id":"019de200-d4e7-7aba-997b-697fce37c98b","probe":"Who signed as Chief Executive Officer of 1847 Holdings LLC?","golden":"Ellery W. Roberts","png_sha":"17421f00db7e68e09f420ba5abd403a8bc79b47f8f380327515bff5297f38fed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"}]},{"eval_id":"019de200-d4e8-7f62-96ae-519b14f37f5f","probe":"On what day of December 2024 did the Guarantors execute this Guaranty?","golden":"13th","png_sha":"17421f00db7e68e09f420ba5abd403a8bc79b47f8f380327515bff5297f38fed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day of December, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day of December, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day of December, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day"}]},{"eval_id":"019de200-d4e9-71c2-9557-1e2c70c1e1fb","probe":"What is the Per RSF Base Rent for the Initial Term?","golden":"$20.50","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)"}]},{"eval_id":"019de200-d4ea-7529-926e-f6d2957fdefe","probe":"Who is the Named Tenant?","golden":"2U Harkins Road LLC","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"}]},{"eval_id":"019de200-d4eb-7ccd-933d-0af15a613cf0","probe":"What is the Alteration Threshold dollar amount?","golden":"$200,000.00","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"}]},{"eval_id":"019de200-d4ec-7fff-aceb-46c812561273","probe":"Which floors of the Building are designated as the Must Take Expansion Premises?","golden":"Floors 5, 6 and 7","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"}]},{"eval_id":"019de200-d4ed-7a5a-bca1-903c35b0c671","probe":"What is the speed limit mentioned in rule 4 of the parking rules?","golden":"5 miles per hour","png_sha":"4a35d25bb27a032bf2661265ea4187cfc0129b1d6aa4a12ae16fc6380aea8e4c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"}]},{"eval_id":"019de200-d4ee-76cd-96ee-560ea13db477","probe":"What are the parking hours listed in rule 1?","golden":"7:30 a.m. to 6:30 p.m., Monday through Friday","png_sha":"4a35d25bb27a032bf2661265ea4187cfc0129b1d6aa4a12ae16fc6380aea8e4c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"}]},{"eval_id":"019de200-d4ef-7bf8-a7ba-27307744e3f9","probe":"What is the 2nd Floor Build-Out Allowance amount?","golden":"$600,000.00","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"}]},{"eval_id":"019de200-d4f0-7baf-9b58-1e08027b6f0d","probe":"How many RSF is the 2nd Floor Premises calculated as for Base Rent purposes?","golden":"12,000 RSF","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"}]},{"eval_id":"019de200-d4f2-7a99-af6e-94a36878aec2","probe":"What is the per-RSF dollar amount used to calculate the Must Take Allowance?","golden":"$46.50","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"}]},{"eval_id":"019de200-d4f3-7347-815c-24a4e9f82950","probe":"In the example, what is the Must Take Allowance for the 7th floor?","golden":"$1,198,611.65","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"}]},{"eval_id":"019de200-d4f4-7dcb-9449-8179714e49d7","probe":"What is the limit of liability for Landlord's commercial general liability insurance?","golden":"$5,000,000 per occurrence","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"}]},{"eval_id":"019de200-d4f5-78f3-8340-3580046edcc8","probe":"What is the each occurrence limit for Personal Injury Liability?","golden":"$9,000,000","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"}]},{"eval_id":"019de200-d4f6-7741-884c-42611e27bcef","probe":"What is the Insured's participation percentage for Personal Injury Liability?","golden":"0%","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"}]},{"eval_id":"019de200-d4f7-7940-b10a-9822b81b3272","probe":"What is the Lobby Renovations Allowance?","golden":"$500,000.00","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"}]},{"eval_id":"019de200-d4f8-7a38-8a19-517016d4b55b","probe":"What is the Initial Build-Out Allowance per RSF?","golden":"$48.00","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"}]},{"eval_id":"019de200-d4f9-7748-a94b-9e4c68688de5","probe":"What is the construction supervision fee percentage Landlord charges on hard construction costs?","golden":"1%","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"}]},{"eval_id":"019de200-d4fa-70fc-b7a8-b9c26c2b14e0","probe":"By what date must Tenant substantially complete the 2nd Floor Build-Out Work?","golden":"April 1, 2018","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"}]},{"eval_id":"019de200-d4fb-7f01-8927-c6d175a34ace","probe":"By what date must Tenant substantially complete the Initial Build-Out Work of the Initial Premises?","golden":"April 1, 2017","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"}]},{"eval_id":"019de200-d4fc-7cca-908f-984e3d8120e7","probe":"What is the umbrella liability each occurrence amount?","golden":"$5,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"}]},{"eval_id":"019de200-d4fd-74c2-abb8-1bb3a38e217c","probe":"What is the medical payments coverage amount?","golden":"$5,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"}]},{"eval_id":"019de200-d4fe-76cb-bdd6-bb011389179c","probe":"What is the fire damage legal liability coverage amount?","golden":"$50,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"}]},{"eval_id":"019de200-d4ff-7fd5-9027-7197160465a2","probe":"What is the automobile liability combined single limit amount?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d500-7cfe-8ff2-d8bbbb64073a","probe":"What is the bodily injury by accident coverage amount per accident under Workers' Compensation Coverage B?","golden":"$500,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"}]},{"eval_id":"019de200-d501-782d-845b-a4e35e143c20","probe":"What is the combined single limit per occurrence for Coverage A under Commercial General Liability?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d502-7a8b-9ba6-c9892e2eeecc","probe":"What insurance form is the general liability insurance to be written on?","golden":"2001 Insurance Services Office form","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the 2001 Insurance Services Office form or its equivalent"}]},{"eval_id":"019de200-d503-798a-afa1-45a2677f34db","probe":"What is the personal and advertising injury liability (Coverage B) amount?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d504-70ea-9d31-b199175fed3c","probe":"In what geographic area must business interruption insurance match amounts customarily carried by responsible tenants?","golden":"Greater Boston","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"}]},{"eval_id":"019de200-d506-744e-be70-a75cf629bab5","probe":"What is the non-refundable assignment/sublease review fee?","golden":"$1,500","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"}]},{"eval_id":"019de200-d508-7af1-93e1-8436c404657e","probe":"How many business days in advance must Tenant provide the Notice of Permitted Transfer?","golden":"10 Business Days","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"}]},{"eval_id":"019de200-d509-782f-8cb5-81249701c47f","probe":"What percentage of the excess must Tenant pay to Landlord as Assignment/Sublease Excess Rent?","golden":"100%","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"}]},{"eval_id":"019de200-d50a-7a93-8a69-a34202f99ee3","probe":"What is the term used for the portion of Premises eliminated under the Elimination Period?","golden":"Eliminated Space","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"}]},{"eval_id":"019de200-d50b-714d-a6f0-8fbb3c33bc67","probe":"What is the term defined for the date immediately prior to the effective date of the proposed assignment?","golden":"Earlier Termination Date","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"}]},{"eval_id":"019de200-d50c-743d-ad76-780e2c2fb12d","probe":"What is the term used for the period after the Elimination Period during which the Eliminated Space is restored to the Premises?","golden":"Restoration Period","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"}]},{"eval_id":"019de200-d50d-7c5f-a9f2-1705d2b33bc2","probe":"What is the term defined for the consideration payable by the assignee or subtenant?","golden":"Assignment/Sublease Consideration","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"}]},{"eval_id":"019de200-d50e-7050-b563-d96d07356800","probe":"How many times per day must the exterior of the building be inspected and maintained?","golden":"four times per day","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"}]},{"eval_id":"019de200-d50f-730f-bba3-567d098ebd36","probe":"By what time each weekday must the stainless steel tops on the 18th Street light boxes be wiped down?","golden":"8:00 AM","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"}]},{"eval_id":"019de200-d510-7320-b95d-f545ed219bc5","probe":"How often must window frames and ledges be swept with a soft-bristled brush on the building exterior?","golden":"Monthly","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"}]},{"eval_id":"019de200-d511-7272-9565-2412f58e253c","probe":"How often must service area floors be dust mopped, at minimum?","golden":"Once per week","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"}]},{"eval_id":"019de200-d512-7496-808b-5b1ea05ca3f8","probe":"How often must standpipe fire hose connections on the exterior of the building be cleaned and polished?","golden":"Weekly","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"}]},{"eval_id":"019de200-d513-7149-ae8c-e8a7754d572b","probe":"What is the minimum amount for a partial prepayment of Revolving Loans?","golden":"$100,000","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"}]},{"eval_id":"019de200-d514-76a5-be6d-0713d4261c08","probe":"What is the full deadline (both time of day and number of business days) by which a Notice of Borrowing must be delivered before a proposed borrowing?","golden":"1:00 p.m. (Eastern time) two (2) Business Days prior","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"}]},{"eval_id":"019de200-d515-7626-bd30-2e0c3b0c3b7f","probe":"Within how many Business Days must Borrower pay any excess if it results from a reserve against the Borrowing Base?","golden":"five (5) Business Days","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"}]},{"eval_id":"019de200-d516-7459-9245-cc659422a55c","probe":"By what time on the Termination Date must the entire outstanding principal of each Revolving Loan be paid?","golden":"12:00 Noon (Eastern time)","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not later than 12:00 Noon (Eastern time)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not later than 12:00 Noon (Eastern time)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"}]},{"eval_id":"019de200-d517-7577-ad4f-c469f0a5f3e3","probe":"What is the higher integral multiple required for partial prepayments of Revolving Loans?","golden":"$25,000","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"}]},{"eval_id":"019de200-d518-778a-9421-02c7d2e3a05a","probe":"What is the section number for 'Time is of the Essence'?","golden":"Section 1.4","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"}]},{"eval_id":"019de200-d519-76a9-b52e-17fb3cd3da08","probe":"What rate do Revolving Loans accrue interest at, plus the Applicable Margin?","golden":"LIBOR Rate","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"}]},{"eval_id":"019de200-d51a-7cbd-841b-aa945ef2b4a8","probe":"Notices of Borrowing must be delivered before what time (Eastern time)?","golden":"1:00 p.m.","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."}]},{"eval_id":"019de200-d51b-7404-9feb-b6384f640f1a","probe":"How many calendar days prior to lease termination must the parties allow Lessor to enter the property for inspection?","golden":"60","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"}]},{"eval_id":"019de200-d51c-7dd7-ad07-e2fd96baf505","probe":"Who conducted the Phase I Environmental Assessment mentioned in section 11.1?","golden":"GAIM REGIOMONTANA","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"}]},{"eval_id":"019de200-d51d-7bbb-9bed-8ceaca14c398","probe":"What is the telephone number listed for Mr. Juan Carlos Gonzalez Quezada?","golden":"(81) 8358.7978","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"}]},{"eval_id":"019de200-d51e-7caf-b475-352d47499736","probe":"What is the postal code (C.P.) listed in the address for Mr. Juan Carlos Gonzalez Quezada?","golden":"66220","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"}]},{"eval_id":"019de200-d51f-723d-9741-37784d76009a","probe":"What is the telephone number listed for Mr. David Rodriguez Santos at Torre Sienna?","golden":"(81) 8356.1200","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"}]},{"eval_id":"019de200-d520-7d78-a11e-ce881c0ff357","probe":"How many calendar days does Lessor have to object to a proposed sublease in writing?","golden":"30","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 calendar days  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 calendar days  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 calendar days  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 calendar days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 calendar days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"}]},{"eval_id":"019de200-d521-77a9-8367-9a4a834e7041","probe":"What is the apartment/interior number (Int.) listed in the address for Torre Sienna?","golden":"1403","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"}]},{"eval_id":"019de200-d522-7ac9-8bba-7b83fb15043b","probe":"What exhibit is the 'Maintenance Carnet' attached as?","golden":"Exhibit \"J\"","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""}]},{"eval_id":"019de200-d523-7d03-9cf0-aa0eb615e454","probe":"Within how many calendar days following lease termination must Lessor conduct and deliver the Phase I environmental assessment under section 11.4?","golden":"fifteen (15) calendar days","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"}]},{"eval_id":"019de200-d524-75fd-bff6-f429befeae8a","probe":"How many calendar days does Lessee have to dispute damages or Alterations indicated in Lessor's notice?","golden":"15","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) calendar days"}]},{"eval_id":"019de200-d525-7710-85f5-fc41b54afbb0","probe":"Within how many calendar days must Lessee deliver a signed counterpart of the sublease agreement to Lessor after its execution?","golden":"five (5) calendar days","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"}]},{"eval_id":"019de22d-8775-7482-9f31-5e7710938d70","probe":"What is the original principal amount of the 3.50% Series A Convertible Senior Notes due February 1, 2018?","golden":"$70.3 million","png_sha":"9999d442e3243c2ea48a7de6c4c9b162568b4e59e41492087837bdb419a11d2c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"}]},{"eval_id":"019de740-e7d8-75d0-835d-3a79745c66cc","probe":"How many consecutive Business Days after Landlord's receipt of the Untenantability Notice are required (in non-Force Majeure cases)?","golden":"five (5)","png_sha":"658d8ecfa29b1c0cf9870b2d1c622a5cff7347859e7674b418cc4660be4eb7b9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) consecutive Business Days"}]},{"eval_id":"019dfae7-e8c3-7289-a5e3-25d26a497795","probe":"What is the fiscal year end date?","golden":"September 28, 2024","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"}]},{"eval_id":"019dfae8-2c75-7590-9083-4c07bf26944a","probe":"What is the Commission File Number?","golden":"001-36743","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"}]},{"eval_id":"019dfae8-8300-75b0-98f0-558c886fd068","probe":"What is the registrant's telephone number?","golden":"(408) 996-1010","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"}]},{"eval_id":"019dfae8-d37e-73db-bad0-7dbbebba1d87","probe":"What is the IRS Employer Identification Number?","golden":"94-2404110","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"}]},{"eval_id":"019dfae9-3119-7c26-b2ed-73fb2888fdfe","probe":"What is the par value per share of Apple's common stock?","golden":"$0.00001","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"}]},{"eval_id":"019dfae9-c244-75c3-92a8-4f02d64471e6","probe":"What were Americas net sales in 2024 (in millions)?","golden":"$167,045","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"}]},{"eval_id":"019dfaea-1b4b-7bef-bf30-f8f1ee1cb9d6","probe":"What were Europe net sales in 2024 (in millions)?","golden":"$101,328","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"}]},{"eval_id":"019dfaea-c282-7bca-85d8-a2edb7306504","probe":"What were total net sales in 2024 (in millions)?","golden":"$391,035","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"}]},{"eval_id":"019dfaeb-1b0e-7077-a093-a8a138a79e25","probe":"What were Greater China net sales in 2022 (in millions)?","golden":"$74,200","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"}]},{"eval_id":"019dfaec-3d80-7c7c-95b7-6a34a086d48b","probe":"What is the date the report was signed?","golden":"November 1, 2024","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"}]},{"eval_id":"019dfaec-8345-7eea-8840-6867945a7a06","probe":"Who is the Director and Chair of the Board?","golden":"Arthur D. Levinson","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"}]},{"eval_id":"019dfaec-e961-7051-a4ce-b66996997cb2","probe":"Who is the Senior Director of Corporate Accounting?","golden":"Chris Kondo","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"}]},{"eval_id":"019dfaed-c27e-7590-9034-1cc2a5319b55","probe":"Who is the accounting firm that signed this consent?","golden":"Ernst & Young LLP","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"}]},{"eval_id":"019dfaee-6467-74cc-8101-5271bea3e394","probe":"What is the Form S-8 number for the Apple Inc. Employee Stock Purchase Plan?","golden":"333-203698","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"}]},{"eval_id":"019dfaef-4f26-7d15-9caf-4928cafc4f5e","probe":"What is the exhibit number shown at the top right of this page?","golden":"Exhibit 23.1","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"}]},{"eval_id":"019dfaf0-11d2-70d1-be50-371940478750","probe":"Where is Braeburn Capital, Inc. incorporated?","golden":"Nevada, U.S.","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."}]},{"eval_id":"019dfaf0-52d8-7941-b336-19bfbe7f8bc1","probe":"Where is Apple Asia Limited incorporated?","golden":"Hong Kong","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"}]},{"eval_id":"019dfaf1-05a1-718d-818a-e45ba4945ba1","probe":"Where is Apple Operations Mexico, S.A. de C.V. incorporated?","golden":"Mexico","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"}]},{"eval_id":"019dfaf2-2642-7eae-b1fb-1620be9706bc","probe":"Starting on what date does this policy apply to Incentive-Based Compensation that is Received?","golden":"October 2, 2023","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"}]},{"eval_id":"019dfaf3-1977-7337-8a56-6b3d55edd900","probe":"What Nasdaq listing rule was adopted to implement Rule 10D-1 under the Exchange Act?","golden":"Listing Rule 5608","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"}]},{"eval_id":"019dfaf3-d93a-7e7a-8293-bed401dc3c74","probe":"Under what year's Securities and Exchange Act is 'executive officer' defined for this policy?","golden":"1934","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"}]},{"eval_id":"019dfaf4-6d06-7bb4-9da0-5703eced16ad","probe":"What company's logo appears at the top of this policy?","golden":"Apple","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"}]},{"eval_id":"019dfaf5-67bd-727d-92f0-43a3108e55cf","probe":"What is the commission file number?","golden":"001-37580","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"}]},{"eval_id":"019dfaf5-e414-73d4-a5bb-864069d83389","probe":"What is the IRS Employer Identification Number?","golden":"61-1767919","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"}]},{"eval_id":"019dfaf6-3c67-7437-b33f-106a71df96cc","probe":"What is the registrant's telephone number?","golden":"(650) 253-0000","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"}]},{"eval_id":"019dfaf6-8eaf-75f8-a68a-e019cf9ab6dc","probe":"What is the interest rate of the Senior Notes due 2064?","golden":"4.375%","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"}]},{"eval_id":"019dfaf6-cd98-71f2-9576-0e07833ebd70","probe":"What is the interest rate of the Senior Notes due 2028?","golden":"2.375%","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"}]},{"eval_id":"019dfaf7-7376-72e6-af9f-4f0302bf05aa","probe":"What is the trading symbol for Alphabet's Class C Capital Stock?","golden":"GOOG","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"}]},{"eval_id":"019dfaf7-a3e9-7079-abc1-1170e6a73c4f","probe":"What is the fiscal year end date on this 10-K?","golden":"December 31, 2025","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"}]},{"eval_id":"019dfaf8-7549-77d5-b050-b8468d035af7","probe":"What was the total amount of Class C share repurchases for the three months ended March 31, 2025?","golden":"$12,535 million","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"}]},{"eval_id":"019dfaf8-f7e3-7fa2-809d-07b2ec3cfaea","probe":"How much remained available for Class A and Class C share repurchases as of March 31, 2025?","golden":"$29.5 billion","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"}]},{"eval_id":"019dfafa-9cb0-7412-8eac-d16591d94510","probe":"What is the quarterly cash dividend declared on April 2025?","golden":"$0.21","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"}]},{"eval_id":"019dfafd-0e8d-7a0f-8f4e-4d3d489b698a","probe":"By what percentage did the Board of Directors increase the quarterly cash dividend in April 2025?","golden":"5%","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"}]},{"eval_id":"019dfafe-5a0c-7b21-8bfa-72a257476e5a","probe":"What was the total carrying value of senior unsecured notes outstanding as of September 30, 2025?","golden":"$23.6 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"}]},{"eval_id":"019dfaff-051e-7ba2-8350-09ebbfdb115a","probe":"How much remained available for Class A and Class C share repurchases as of September 30, 2025?","golden":"$74.8 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"}]},{"eval_id":"019dfb00-8129-7fae-9c3d-085f17af7163","probe":"How many Class C shares were repurchased in the three months ended September 30, 2025 (in millions)?","golden":"51","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"}]},{"eval_id":"019dfb01-6670-7c43-bf57-578d4e8743df","probe":"How much was the revolving credit facility expiring in April 2030?","golden":"$6.0 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"}]},{"eval_id":"019dfb02-8211-7651-9ec4-8c0ebcf58a3b","probe":"What was the dollar amount of Class A share repurchases for the three months ended September 30, 2025 (in millions)?","golden":"$926","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"}]},{"eval_id":"019dfb06-2d63-7e40-9cfc-442adddd3a61","probe":"As of what date did the CEO and CFO conclude on the disclosure controls evaluation?","golden":"June 30, 2025","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"}]},{"eval_id":"019dfb06-7255-7580-9ef1-58f24ae75626","probe":"What rule under the Exchange Act was used to evaluate disclosure controls and procedures?","golden":"Rule 13a-15","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"}]},{"eval_id":"019dfb07-58e1-741b-95ae-39f6ad5b9738","probe":"For what quarter ended date is the internal control reporting statement made?","golden":"June 30, 2025","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"}]},{"eval_id":"019dfb08-723b-72c9-8209-4c6b104c74d9","probe":"What form is the Quarterly Report on?","golden":"Form 10-Q","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"}]},{"eval_id":"019dfb09-b2b4-7900-94d0-5ead62b5fa3a","probe":"How much was the initial investment used in the graph comparison?","golden":"$100","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"}]},{"eval_id":"019dfb0a-1542-7607-afff-3824643328be","probe":"On what date does the graph's tracking period end?","golden":"December 31, 2025","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"}]},{"eval_id":"019dfb0a-4250-7161-8e90-fa2502ad8254","probe":"What is the starting date of the graph's tracking period?","golden":"December 31, 2020","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"}]},{"eval_id":"019dfb0a-bbec-7b6d-bb26-274ff05f9459","probe":"What is the highest dollar value shown on the y-axis of the graph?","golden":"$400","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"}]},{"eval_id":"019dfb0a-e54b-7973-8d05-99144d938deb","probe":"What color is the line representing the S&P 500 in the graph?","golden":"Green","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"}]},{"eval_id":"019dfb0b-0fe9-717a-b315-903647d9114e","probe":"What color is the line representing Alphabet Inc. Class C in the graph?","golden":"Red","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"}]},{"eval_id":"019dfb0b-9664-7b20-bea5-647276953368","probe":"How much is Alphabet acquiring Wiz, Inc. for?","golden":"$32.0 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"}]},{"eval_id":"019dfb0c-07a8-768c-bf46-7d82769ad116","probe":"What is the long-term income taxes payable as of December 31, 2025?","golden":"$9.5 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"}]},{"eval_id":"019dfb0d-123a-74db-8a55-4a162b6b8cfb","probe":"How much is Alphabet acquiring Intersect for in cash?","golden":"$4.8 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"}]},{"eval_id":"019dfb0d-98a6-7573-8987-ba32c57f6b7a","probe":"What is the total amount of purchase commitments and other contractual obligations as of December 31, 2025?","golden":"$149.1 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"}]},{"eval_id":"019dfb0e-3ccc-74fa-9d0d-91c2663bea11","probe":"What was the total revenue for the three months ended March 31, 2025?","golden":"$90,234 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"}]},{"eval_id":"019dfb10-1fb2-7986-b06c-55501bbd796e","probe":"What was the United States revenue for the three months ended September 30, 2025?","golden":"$48,758 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"}]},{"eval_id":"019dfb11-8ce1-72d9-b0ab-fc0be563e187","probe":"What were the total revenues for the nine months ended September 30, 2025?","golden":"$289,007 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"}]},{"eval_id":"019dfb14-6817-7cc7-90e2-fce76cd476e7","probe":"How many employees did JPMorganChase have globally as of December 31, 2025?","golden":"318,512","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"}]},{"eval_id":"019dfb14-a085-7b52-8f76-6678f2a4de9c","probe":"How many employees does JPMorganChase have in North America?","golden":"185,208","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"}]},{"eval_id":"019dfb14-f2e3-7cee-a27e-79e81867b37a","probe":"How many employees work in CCB?","golden":"144,196","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"}]},{"eval_id":"019dfb15-3908-7fc5-93bd-052705ae9929","probe":"In how many countries are JPMorganChase's employees located?","golden":"66","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"}]},{"eval_id":"019dfb15-75a7-7c29-a2ca-90c32df63ac5","probe":"What percentage of total employees are women?","golden":"48%","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"}]},{"eval_id":"019dfb15-c7c7-74ee-b29b-e7b5d8c9a152","probe":"How many employees work in the Asia-Pacific region?","golden":"96,499","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"}]},{"eval_id":"019dfb16-cbe3-7d4d-a23d-2234c2d7d297","probe":"What is the first bulleted item under the list of electronic and internet-based financial solutions?","golden":"lending and other extensions of credit to consumers","png_sha":"704943f48019c6bab8cb509e1ddeb6f9b48085007ac9101976ed3d04798ac274","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"}]},{"eval_id":"019dfb17-0cc4-74a1-8d62-afab29ef1e82","probe":"What is the third bulleted item under the list of electronic and internet-based financial solutions?","golden":"cryptocurrency, including stablecoins","png_sha":"704943f48019c6bab8cb509e1ddeb6f9b48085007ac9101976ed3d04798ac274","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"}]},{"eval_id":"019dfb18-cb9a-7558-a5ce-7b4911abc1ba","probe":"What was the total assets under management in 2025 (in billions)?","golden":"$4,791","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"}]},{"eval_id":"019dfb19-eada-7639-80c1-d416915f2795","probe":"How many client advisors were there as of December 31, 2025?","golden":"10,150","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"}]},{"eval_id":"019dfb1a-7fed-744e-a7bc-585de30578fb","probe":"What was the equity assets value in 2025 (in billions)?","golden":"$1,400","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"}]},{"eval_id":"019dfb1a-d4b4-7ee1-b950-3f3208c24be4","probe":"What was the reported net interest income in 2025 (in millions)?","golden":"$95,443","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"}]},{"eval_id":"019dfb1b-4a0a-766a-92cd-c2e37df27c36","probe":"What was the net yield on average interest-earning assets on a managed basis in 2025?","golden":"2.50%","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"}]},{"eval_id":"019dfb1b-9e1c-704c-b958-e7a06540c65f","probe":"What was the Memo: Total Markets net revenue in 2025 (in millions)?","golden":"$35,782","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"}]},{"eval_id":"019dfb1c-4c58-739f-8241-e4a688fff415","probe":"What was the noninterest revenue excluding Markets in 2023 (in millions)?","golden":"$44,361","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"}]},{"eval_id":"019dfb1d-0b1b-7540-9211-41f0ac069d15","probe":"In what year was MetLife, Inc. incorporated in Delaware?","golden":"1999","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"}]},{"eval_id":"019dfb1d-fe01-7745-a248-c6531ebdce43","probe":"What act is referenced as the source of the 'forward-looking statements' definition?","golden":"Private Securities Litigation Reform Act of 1995","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"}]},{"eval_id":"019dfb1e-4042-7d24-95d6-9213cb5fb946","probe":"How many factors are listed on this page?","golden":"22","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"}]},{"eval_id":"019dfb1e-d54d-73fd-8f17-16eb21390c86","probe":"What is factor number 10 in the list?","golden":"London Interbank Offered Rate discontinuation and transition to alternative reference rates","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"}]},{"eval_id":"019dfb1f-5f66-79ad-be34-3c4e429dbcac","probe":"How old is Steven J. Goulart?","golden":"64","png_sha":"8a8df5c53ffc88bd982b700c7adc729d6f1a78da7ebcbf1ee0a1a778e2017590","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"}]},{"eval_id":"019dfb20-e27a-7c39-b2f6-4f9d7929ea4e","probe":"What is the estimated fair value of total fixed maturity securities AFS as of December 31, 2022?","golden":"$276,780 million","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$276,780 million"}]},{"eval_id":"019dfb22-1d21-7795-bb3e-bdc661245cb9","probe":"What is the % of Total for Aaa/Aa/A rated securities as of December 31, 2021?","golden":"70.4%","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"}]},{"eval_id":"019dfb23-4f44-7d83-91d3-79100e6cffec","probe":"What were the adjusted earnings available to common shareholders for the U.S. segment?","golden":"$2,996 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"}]},{"eval_id":"019dfb23-8371-717a-825f-6e20e45dcb5f","probe":"What is the U.S. segment's percentage contribution to total segment level adjusted earnings?","golden":"47%","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"}]},{"eval_id":"019dfb23-d976-764b-875f-1c7d8d24b80e","probe":"What were the adjusted earnings for the Asia segment?","golden":"$1,378 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"}]},{"eval_id":"019dfb24-353e-721c-af95-7c83f5c7c811","probe":"What were the adjusted earnings for the EMEA segment?","golden":"$246 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"}]},{"eval_id":"019dfb29-7d6d-77ed-abe1-9e196503fe98","probe":"What is American Life Insurance Company's Moody's rating?","golden":"A1","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"}]},{"eval_id":"019dfb29-d233-7190-9c54-414c50184509","probe":"What is Metropolitan Life Insurance Company's Fitch rating?","golden":"AA-","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"}]},{"eval_id":"019dfb2a-30eb-73bc-9534-9a1a79fcefd9","probe":"What is Metropolitan Tower Life Insurance Company's Moody's rating?","golden":"Aa3","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"}]},{"eval_id":"019dfb3c-0056-7fd4-8497-80ad7e52deed","probe":"What is the date on the letter?","golden":"September 12, 2025","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"}]},{"eval_id":"019dfb3c-443c-749d-9922-e22f48da574a","probe":"What is the total amount of expenses stated in the letter?","golden":"$537.6 billion","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"}]},{"eval_id":"019dfb3c-e409-7e70-93e0-584a7b66e218","probe":"What is the fax number listed at the bottom of the letter?","golden":"916.322.4404","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"}]},{"eval_id":"019dfb3d-df1d-70c3-8680-871f110c4e18","probe":"How many state departments are involved in the ACFR production, according to the letter?","golden":"more than 200","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"}]},{"eval_id":"019dfb41-090f-742c-a295-a841b0d40942","probe":"What is the last year the ACFR publication target date in March was achieved, according to the letter?","golden":"2018","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"}]},{"eval_id":"019dfb42-0697-72fe-ace9-658c5975fe72","probe":"What is the General fund balance as previously reported on 6/30/2023?","golden":"$64,003,688","png_sha":"4d385e9f1f0ded0edf6cd42e1fce98d308714a9c9a90264d60830da6a87b20a5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"}]},{"eval_id":"019dfb42-9508-70e6-ba0b-e32a83de1982","probe":"What is the Pension/OPEB balance as previously reported on 6/30/2023?","golden":"$826,165,564","png_sha":"4d385e9f1f0ded0edf6cd42e1fce98d308714a9c9a90264d60830da6a87b20a5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"}]},{"eval_id":"019dfb45-c922-797e-8c28-c8e8919e6e6b","probe":"What was the General Fund's ending fund balance for fiscal year 2023-24?","golden":"$63.4 billion","png_sha":"be9e4b96b82c2251ae314ddc72ad643547069399fbff67cb23663b4b60410b07","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"}]},{"eval_id":"019dfb48-c7e6-72a9-8f31-8e936894de0c","probe":"What was the total primary government net position in 2006 (in thousands)?","golden":"$48,552,143","png_sha":"6ded8b72d8724efb0a5addcabb85b9fb055c8702b034b32a8bd9d35ae7b3b2d4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"}]},{"eval_id":"019dfb49-36d0-787d-9b10-263d0dc86158","probe":"What was the total business-type activities net position in 2005 (in thousands)?","golden":"$9,638,143","png_sha":"6ded8b72d8724efb0a5addcabb85b9fb055c8702b034b32a8bd9d35ae7b3b2d4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"}]},{"eval_id":"019dfb49-c621-751e-8311-221426895f61","probe":"What date does the fiscal year end?","golden":"June 30, 2013","png_sha":"e78f4e20277a031b7f8a1c8ec01e35359d5db802026c772a280aa46b2e15036d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"}]},{"eval_id":"019dfb4a-c5b5-77b8-8666-73fe5ecf7295","probe":"What word appears on the banner above the figure in the seal?","golden":"EUREKA","png_sha":"e78f4e20277a031b7f8a1c8ec01e35359d5db802026c772a280aa46b2e15036d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"}]},{"eval_id":"019dfb4c-a89f-7747-8ca3-fb374afbe129","probe":"How many employees were in the Services industry in 2012?","golden":"6,219,000","png_sha":"ee102138e4471a718761ff29297490e756f20be442c4eab71f74ad7b88ef9337","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"}]},{"eval_id":"019dfb4d-3d6b-7988-bb66-c81ee4e34bf7","probe":"How many employees were in Manufacturing in 2003?","golden":"1,544,500","png_sha":"ee102138e4471a718761ff29297490e756f20be442c4eab71f74ad7b88ef9337","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"}]},{"eval_id":"019dfff9-bbf0-7f8f-9eeb-4283d498732d","probe":"What is the General Fund amount due from primary government to University of California?","golden":"$169,215","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215"}]},{"eval_id":"019dfffa-9fa6-7a63-a87b-53eda9047796","probe":"What is the amount from Nonmajor governmental funds due to University of California?","golden":"36,988","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"}]},{"eval_id":"019dfffb-b244-7a37-903d-2e6addf12282","probe":"What was the net general bonded debt per capita in 2018?","golden":"$2,042","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"}]},{"eval_id":"019dfffc-0d62-7f14-a566-4e70db84b399","probe":"What was the net general bonded debt as a percentage of personal income in 2015?","golden":"4.0%","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"}]},{"eval_id":"019dfffc-678a-79c5-aaea-473c3f22a054","probe":"What was the General obligation bonds amount in 2017?","golden":"$79,503,871","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871"}]},{"eval_id":"019dfffc-e4bf-79ad-8c4e-89d704ac54ed","probe":"What is at the top of the Texas government structure chart?","golden":"The Electorate","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"}]},{"eval_id":"019dfffe-6b06-706f-a135-e5934397dcc8","probe":"What body sits directly below the Legislature on the chart, alongside the State Auditor's Office?","golden":"Legislative Committees","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"}]},{"eval_id":"019dffff-a90b-7567-a8fa-d73e11996c14","probe":"What body is shown at the very bottom of the Legislative branch chart?","golden":"Sunset Advisory Commission","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"}]},{"eval_id":"019e0000-52c3-755e-9a98-534e00107784","probe":"What is the total pass-through to other agencies?","golden":"$254,334.30","png_sha":"cee789f33becc6e55d762115a7b119808f36099b5c736f4b0ec740bce52a004c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"}]},{"eval_id":"019e0001-dddd-7fec-b736-f93ff293500f","probe":"What was the balance in the ESF fund on Aug. 31, 2024?","golden":"$23.8 billion","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"}]},{"eval_id":"019e0002-846c-7a5c-bcd2-21cf9dab8b63","probe":"What was the Texas unemployment rate as of November 2024?","golden":"4.2 percent","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"}]},{"eval_id":"019e0003-4dd3-73ec-8ba4-bf652587ad06","probe":"By how much is Texas' population projected to grow in 2025?","golden":"376,600","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"}]},{"eval_id":"019e0008-27fa-70f4-8421-41777f7bcace","probe":"What office is shown in pink under the First Deputy Mayor?","golden":"Office of Efficiency","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"}]},{"eval_id":"019e0009-2f8e-768d-8762-ff9e82bcea2b","probe":"What is the SAO Report Number?","golden":"25-316","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"}]},{"eval_id":"019e0009-af38-766a-9ac7-cb0908ad2999","probe":"What percent of the assets of the Colleges and Universities does the University of Texas System constitute?","golden":"72.9 percent","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"}]},{"eval_id":"019e000a-7052-7138-b0db-733f874d02cd","probe":"What percent of the expenditures for the State Highway Fund does the Texas Department of Transportation constitute?","golden":"99.9 percent","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"}]},{"eval_id":"019e000b-d49b-7660-82c4-81ecfb04a236","probe":"What percentage of revenue comes from Charges for Services in Graph MDA-6?","golden":"59.7%","png_sha":"3f8e2c78a2134ddb79f740cc731c989a29e5b11d89cdb0254e1f1740d44cfdb0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"}]},{"eval_id":"019e000d-e61a-7a45-b84f-1c881c74e271","probe":"What is the fair value of Private Equity investments (in thousands)?","golden":"$76,309,756","png_sha":"1993d56fb3f7471f5844aa6a62bb8dd9a43b4784dac30f107664bca458bf68ea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"}]},{"eval_id":"019e000e-f859-77f7-aa7c-927c51e130e8","probe":"What is the unfunded commitment for Energy, Natural Resources, Infrastructure (in thousands)?","golden":"$11,460,123","png_sha":"1993d56fb3f7471f5844aa6a62bb8dd9a43b4784dac30f107664bca458bf68ea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"}]},{"eval_id":"019e0010-c825-72aa-a139-0e4ab295b2dc","probe":"What is the minimum aggregate floor area required by the CEP program?","golden":"25,000 square feet","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"}]},{"eval_id":"019e0011-2a92-7ac7-89be-ac4f2296baea","probe":"Under the CRP/CEP programs, by how much were the City's tax revenues reduced in 2024 (in thousands)?","golden":"$12,500","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"}]},{"eval_id":"019e0011-cff1-7126-8235-02b26f0fbab9","probe":"What year did ICAP replace ICIP?","golden":"2008","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"}]},{"eval_id":"019e0017-450f-737d-a346-38c48007c835","probe":"Under the CRP program, what is the per-square-foot dollar amount used in the base abatement calculation formula?","golden":"$2.50","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."}]},{"eval_id":"019e0018-17a0-7847-a0b3-11f039bc48a6","probe":"What is the page number shown at the bottom of this page?","golden":"128","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"}]},{"eval_id":"019e0019-d170-7146-8e38-cc44276e6018","probe":"Under the CRP/CEP programs, by how much were the City's tax revenues reduced as a result of abatement agreement in 2024 (in thousands)?","golden":"$12,500","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"}]},{"eval_id":"019e001b-3183-79f1-a745-4e066a6ce3ef","probe":"What is the Executive Order number mentioned in the letter?","golden":"2025-1","png_sha":"781c6fcbd4f3164179bf71cd942ca2e9794fc7c49c6bbcf883dd13f2ce626331","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"}]},{"eval_id":"019e001b-77bc-7c11-843b-51dfbbec15c3","probe":"Who signed this letter?","golden":"Mayor Brandon Johnson","png_sha":"781c6fcbd4f3164179bf71cd942ca2e9794fc7c49c6bbcf883dd13f2ce626331","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"}]},{"eval_id":"019e001d-d405-7881-ab8b-abcb0d7e70e1","probe":"What is Deloitte's fax number listed on the page?","golden":"+1 312 486 1486","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"}]},{"eval_id":"019e001f-f83d-78ad-bad5-21b87bdb9833","probe":"According to the auditor's report, the Pension Trust Funds represent what percentages of the assets, financial position, and revenues respectively?","golden":"92%, 100%, and 72%","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"}]},{"eval_id":"019e0020-bffb-7733-931f-63dac6e0f8f0","probe":"Who is the report addressed to as Mayor?","golden":"Brandon Johnson","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"}]},{"eval_id":"019e0027-f41a-7a7a-b3f6-f9b59cde341b","probe":"What is the experience study period for the Policemen's plan?","golden":"January 1, 2019 - December 31, 2023","png_sha":"2aded5f520cbaa023e8d0c1e94f15e68ccafa9f34d1e6736781e6f894512fe8e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"}]},{"eval_id":"019e0028-b45f-7292-959c-f04db8d08d19","probe":"What is the experience study period for the Laborers' plan?","golden":"January 1, 2017 - December 31, 2019","png_sha":"2aded5f520cbaa023e8d0c1e94f15e68ccafa9f34d1e6736781e6f894512fe8e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"}]},{"eval_id":"019e002a-8546-75d0-9290-e4f34687786f","probe":"What year ended is referenced at the top of the page?","golden":"December 31, 2024","png_sha":"4ceaa28bf7551920a1890b7fbf19a27b1cc875ad22828548d20d5021ffb4cb9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"}]},{"eval_id":"019e002e-34d1-7c51-ba48-bffeca76fb26","probe":"What was the loans receivable balance of the CCCF as of December 31, 2024?","golden":"$3.1 million","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"}]},{"eval_id":"019e002e-ef48-7527-8160-cb77c6e44245","probe":"On what date did the City of Chicago City Council adopt the ordinance organizing the STSC?","golden":"October 11, 2017","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"}]},{"eval_id":"019e0030-d1da-7720-bec1-d70663e3456a","probe":"On what date did the City Council adopt the CCCF Ordinance?","golden":"November 16, 2016","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"}]},{"eval_id":"019e0033-8f40-79d7-8505-50112ded8060","probe":"What is the website where complete financial statements of the STSC can be obtained?","golden":"www.salestaxsecuritizationcorporation.com","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"}]},{"eval_id":"019e003a-5da3-7d08-9f15-665248ccb0cf","probe":"What was the final budgeted Vehicle Tax amount under Transportation Tax (in thousands)?","golden":"$128,777","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"}]},{"eval_id":"019e003a-e619-7c9f-b4b2-aa2807d3bff9","probe":"What was the actual Motor Fuel Tax and Project revenue under Transportation Tax (in thousands)?","golden":"$122,483","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"}]},{"eval_id":"019e003c-6cc9-782c-bca0-875bef94c76c","probe":"What was the final budgeted MEABF Pension Reserve under Special Area and Utility Taxes (in thousands)?","golden":"$216,275","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"}]},{"eval_id":"019e003d-55d2-7007-b3b6-dc37892643d2","probe":"Who is the Chief Actuary?","golden":"Marek Tyszkiewicz","png_sha":"89c77daf9c6f881f0116f445cbf736cffc12698b60a93b437699a1a075b00138","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"}]},{"eval_id":"019e003f-44df-7a8d-a15c-ff2dc3cf553b","probe":"What is the funded ratio for the 2022 valuation date?","golden":"85.1%","png_sha":"13c08f8d02fa78d2fc1f1b9783d494af4a43f3083f75509ffac06a9ae415320f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"}]},{"eval_id":"019e0040-0266-795a-b6d2-549f195f8032","probe":"What percentage of the Police Superior Officers' Variable Supplements Fund is held in Collective Trust Funds?","golden":"59.28%","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"}]},{"eval_id":"019e0040-6668-7abd-8cd8-dd05d069c1c1","probe":"What is the dollar amount of Equity Securities in the Police Officers' Variable Supplements Fund?","golden":"$771,119","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"}]},{"eval_id":"019e0041-2237-71d4-8880-cb8564c7b0ae","probe":"What is the dollar amount of Short-Term Investments in the Police Superior Officers' Variable Supplements Fund?","golden":"$8,441","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"}]},{"eval_id":"019e0042-1c07-71d9-8683-e990abab4862","probe":"What is the Reduced Service Retirement probability at 20 years of service?","golden":"5.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"}]},{"eval_id":"019e0043-db39-746e-8a90-d9b8e9e16e2f","probe":"What is the Unreduced Before Full Escalation probability at 22 years of service?","golden":"5.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"}]},{"eval_id":"019e0044-11fe-7039-99f0-4014e1cca342","probe":"What is the Reduced Service Retirement probability at 21 years of service?","golden":"2.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"}]},{"eval_id":"019e0045-18ce-7ff9-90d3-7a8a76d3a7b2","probe":"What is the As Restated Total Liabilities amount?","golden":"54,689,670","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"}]},{"eval_id":"019e0046-8a1d-76f7-a894-dfdf17c5e779","probe":"What is the As Previously Stated Unrestricted (Deficit) amount (in thousands of dollars)?","golden":"(33,888,893)","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"}]},{"eval_id":"019e0048-5d8d-7e41-bfac-807538f6bc7d","probe":"What is the required year of adoption for GASB Statement No. 102?","golden":"2025","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"}]},{"eval_id":"019e0049-7334-7204-a87d-cdd77f11d1df","probe":"What is the As Restated Total Net (Deficit)/Position amount (in thousands)?","golden":"$(30,877,248)","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"}]},{"eval_id":"019e004a-3183-7f93-ae28-888547cf9f69","probe":"What is the As Previously Stated Accrued and Other Liabilities amount (in thousands)?","golden":"$2,037,352","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"}]},{"eval_id":"019e004b-c349-7e93-af8d-24a8c0227413","probe":"Who is the Chairman of the Texas Transportation Commission?","golden":"J. Bruce Bugg, Jr.","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."}]},{"eval_id":"019e004c-1788-7c26-832d-effce8fee9e9","probe":"What city is Commissioner Robert C. Vaughn from?","golden":"Dallas","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"}]},{"eval_id":"019e004c-7b29-737b-b3c2-4cb5677b686a","probe":"What city is Commissioner Steven D. Alvis from?","golden":"Houston","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"}]},{"eval_id":"019e004e-6fac-7e8f-a9ed-7aab75af118d","probe":"What is the Total Foreign Currency Risk for Fiduciary Funds (in thousands)?","golden":"$454,100","png_sha":"14dd94971a85d5333d42a72d87ae42c4f4cf19684f10114f6d12e3dc0dcfbba3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454,100  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454,100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454,100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454,100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454,100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"}]},{"eval_id":"019e004f-570b-7494-b4dc-1980043719cb","probe":"What is the Component Units amount for Uninsured and Uncollateralized in Table 3A (in thousands)?","golden":"$729,847","png_sha":"14dd94971a85d5333d42a72d87ae42c4f4cf19684f10114f6d12e3dc0dcfbba3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"}]},{"eval_id":"019e0050-7b43-7b4a-b132-8ba0d44ecc08","probe":"What is the Total Fund Balance \u2013 Governmental Funds (in thousands)?","golden":"$98,174,085","png_sha":"2e5b15b0fe9ca40f66bc4f99fea40f7e0fb26c9abe4ac75ea6dad2ab72ae36d6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98,174,085  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98,174,085"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"}]},{"eval_id":"019e007c-e48c-710f-9404-90a2a810ccb4","probe":"What is the Net Position of Governmental Activities (in thousands)?","golden":"$134,878,410","png_sha":"2e5b15b0fe9ca40f66bc4f99fea40f7e0fb26c9abe4ac75ea6dad2ab72ae36d6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"}]},{"eval_id":"019e007d-9a24-752a-89d4-7fe852700caa","probe":"What is the total revenue shown in the Revenue by Source pie chart?","golden":"$190.5 Billion","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"}]},{"eval_id":"019e007d-e19f-7d15-815d-b4e94383d99b","probe":"What are the total expenses for Health and Human Services?","golden":"$75,194 million","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"}]},{"eval_id":"019e007e-1a80-7e4b-98c2-9c3f2d812c06","probe":"What percentage of revenue came from Taxes?","golden":"42.7%","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"}]},{"eval_id":"019e007e-aac9-7785-8c44-edb9f9dfe20d","probe":"What are the total expenses across all governmental activities?","golden":"$154,896","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"}]},{"eval_id":"019e007f-3589-7306-b64b-6253528585e4","probe":"What page is Risk Factors on?","golden":"14","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"}]},{"eval_id":"019e007f-7683-7d10-a251-ff6bdde0aca0","probe":"What page is Executive Compensation on?","golden":"105","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"}]},{"eval_id":"019e007f-b345-710c-b63d-5812e55e82ef","probe":"What page is Financial Statements and Supplementary Data on?","golden":"48","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"}]},{"eval_id":"019e0080-81ba-7bac-bba1-8cc2e8324436","probe":"What page is the Budgetary Comparison \u2013 General Fund on?","golden":"47","png_sha":"0a460adc7db810670c579dc36d27c02a4097bb3e02f77fbbeacd84bbcc9d2f0e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"}]},{"eval_id":"019e0080-b0bf-7f30-a02e-a2ed8dcea371","probe":"What page is the Schedule of Employee Benefits \u2013 All Funds on?","golden":"56","png_sha":"0a460adc7db810670c579dc36d27c02a4097bb3e02f77fbbeacd84bbcc9d2f0e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"}]},{"eval_id":"019e0083-0a96-77f4-a106-fb583482c798","probe":"How much did the General Land Office (GLO) increase?","golden":"$860 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"}]},{"eval_id":"019e0083-5461-7354-8851-9512e63b1c22","probe":"How much did the Texas Commission on Environmental Quality (TCEQ) increase?","golden":"$543 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"}]},{"eval_id":"019e0083-c942-7b97-83f8-c0423a20e2a4","probe":"How much did the Federal Emergency Management Agency (FEMA) decrease?","golden":"$420 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"}]},{"eval_id":"019e0084-65de-77d8-92f6-79df23bc1fad","probe":"What is the phone number for Pattillo, Brown & Hill, L.L.P.?","golden":"254.772.4901","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"}]},{"eval_id":"019e0084-dffc-7ecf-b0c1-44b81836ebdd","probe":"What is the date of the year ended for the audit?","golden":"September 30, 2024","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"}]},{"eval_id":"019e009f-5030-795d-b32e-68b8c8725b1a","probe":"What is the page number shown at the bottom right?","golden":"H261","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"}]},{"eval_id":"019e00a0-6d47-7a01-8cdb-9db00cf90181","probe":"Which bill number is referenced as the 'Born-Alive Abortion Survivors Protection Act'?","golden":"H.R. 21","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"}]},{"eval_id":"019e00a1-03cf-7de0-9353-8ede1f29d21e","probe":"What time did the House meet?","golden":"10 a.m.","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."}]},{"eval_id":"019e00a2-46eb-7c4d-93dc-be4b015c5931","probe":"Until what time may morning-hour debate continue?","golden":"11:50 a.m.","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."}]},{"eval_id":"019e00a2-8827-7350-ac1d-d1e691c7bc93","probe":"Which Congress's proceedings does this issue cover?","golden":"119th","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, first session"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress, First Session"}]},{"eval_id":"019e00a3-4654-7104-90ff-d36264aea63f","probe":"Who did Speaker Mike Johnson appoint as Speaker pro tempore for the day?","golden":"Nathaniel Moran","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran"}]},{"eval_id":"019e00a4-39cf-73f5-a08d-bdaf6f0e9555","probe":"Which state is Mrs. Trahan from?","golden":"Massachusetts","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"}]},{"eval_id":"019e00a4-9927-7270-b177-688639d2d84a","probe":"Which state is Mr. Thompson from?","golden":"Pennsylvania","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"}]},{"eval_id":"019e00a4-d8d8-7d76-84d9-c255fd95f7cd","probe":"How many minutes is Mrs. Trahan recognized for?","golden":"5 minutes","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"}]},{"eval_id":"019e00a5-86fd-7ef3-9421-534e8a66b6ef","probe":"How many 'yeas' were there in Roll No. 20?","golden":"214","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"}]},{"eval_id":"019e00a5-ff31-72d6-b137-910bed3336e6","probe":"How many representatives were 'not voting' in Roll No. 20?","golden":"15","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"}]},{"eval_id":"019e00a6-329c-73a0-9a01-cd95583196e9","probe":"How many 'nays' were there in Roll No. 20?","golden":"204","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"}]},{"eval_id":"019e00a7-701e-7774-bdaa-4a60fe45e545","probe":"What is the page number shown at the top left?","golden":"H276","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"}]},{"eval_id":"019e00a7-fb7c-797d-8520-954d5503a748","probe":"What is the Roll number for the vote shown on this page?","golden":"20","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"}]},{"eval_id":"019e00ac-04dd-7f1d-bcec-9be7f5c1f3ce","probe":"Did Aderholt vote yea or nay?","golden":"yea","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"}]},{"eval_id":"019e00ac-a893-7e85-9fc2-0de0e7d020dd","probe":"Did Cherfilus-McCormick vote yea or nay?","golden":"nay","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"}]},{"eval_id":"019e00ad-32af-76df-9057-a199ce91dd17","probe":"How many \"Garcia\" members are listed in the NAYS column?","golden":"3","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"}]},{"eval_id":"019e00ad-d3ed-7216-853a-30e02dbd1131","probe":"Who is the first name listed alphabetically in the NAYS column?","golden":"Adams","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"}]},{"eval_id":"019e00b0-cecb-7e7c-8149-7640c1dad861","probe":"Which member changed their vote from \"nay\" to \"yea\"?","golden":"Mr. Palmer","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"}]},{"eval_id":"019e00b3-c235-73fb-ba21-0118c8eadbf3","probe":"What is the page number shown in the top-left corner?","golden":"S250","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"}]},{"eval_id":"019e00b4-9c27-73de-8223-11187c914c6f","probe":"What is the date shown at the top-right of the page?","golden":"January 20, 2025","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"}]},{"eval_id":"019e00b9-b13c-7e4a-bf11-475eea29d6d3","probe":"Did Senator McConnell vote yea or nay on the final passage of S. 5?","golden":"yea","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"}]},{"eval_id":"019e00bb-59ee-702a-8cec-38e372b26db8","probe":"How many senators voted YEA on Amendment No. 8?","golden":"75","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"}]},{"eval_id":"019e00bb-a83a-79e5-808d-25352081e864","probe":"How many senators voted NAY on the final passage of S. 5?","golden":"35","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"}]},{"eval_id":"019e00bc-df61-7504-ab8f-56af050077d7","probe":"Who is being considered for Secretary of State on Executive Calendar No. 2?","golden":"Marco Rubio","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO of Florida"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"}]},{"eval_id":"019e00bf-a471-719a-84c8-972702dced95","probe":"What dollar amount is mentioned as the threshold for financial harm to a State or its residents?","golden":"$100","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"}]},{"eval_id":"019e00c1-687b-7e30-917e-677d5c514e5a","probe":"Who asked for the yeas and nays on the vote for S. 5?","golden":"Mrs. Britt","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt"}]},{"eval_id":"019e00c1-d9d4-7426-9471-e13471bf2c6f","probe":"How many nays were there on the vote on Amendment No. 8?","golden":"24","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"}]},{"eval_id":"019e00c6-1e73-73ec-8e95-413c88e39426","probe":"How much did the Wesley Hunt Victory Fund contribute on 2/3/2025?","golden":"$25,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"}]},{"eval_id":"019e00c6-5871-7da2-a93b-3aefb5c66f16","probe":"What is the page number shown at the top left?","golden":"S2714","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"}]},{"eval_id":"019e00c8-3f2a-7e4f-b0e4-86c796356894","probe":"How much did the Connecticut Republican State Central Committee transfer on 9/27/2024?","golden":"$10,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"}]},{"eval_id":"019e00c9-4d63-7e78-a3b2-fd24f554e0db","probe":"What was the largest single contribution amount listed in the Spouse section?","golden":"$25,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"}]},{"eval_id":"019e00c9-c213-7e12-b66f-043b2559c706","probe":"Who is being nominated to be Lieutenant Commander in the Coast Guard?","golden":"John O. Mansolillo","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"}]},{"eval_id":"019e00ce-9d49-7844-bd6c-346e75c0b284","probe":"What is the bill number for the bill to direct the Secretary of the Treasury to stop minting the penny?","golden":"S. 1525","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"}]},{"eval_id":"019e0518-b40f-7b97-99f0-2cd141711ff0","probe":"What is the bill number for the bill to regulate assault weapons?","golden":"S. 1531","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"}]},{"eval_id":"019e051c-6f18-78b3-a1d7-9d8a0a2b9618","probe":"How many senators voted yea on the Driscoll nomination?","golden":"66","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"}]},{"eval_id":"019e051d-3c27-7462-be35-0be6eece26b9","probe":"How many senators were listed as NOT VOTING?","golden":"6","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"}]},{"eval_id":"019e051d-a887-715d-88bf-933cc563b087","probe":"How many nays were there in the vote?","golden":"28","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"}]},{"eval_id":"019e051e-38d3-7d68-9805-50585c912e12","probe":"How would Senator Cruz of Texas have voted if present?","golden":"yea","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"}]},{"eval_id":"019e0520-1d4b-7483-9ed6-1c012178bbd9","probe":"How many years has Jess Andrews run Senator Kennedy's communications shop?","golden":"5 years","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"}]},{"eval_id":"019e0520-d920-72fd-9146-7ff4401c225d","probe":"Did Senator Booker vote yea or nay on the Driscoll nomination?","golden":"nay","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"}]},{"eval_id":"019e0523-07a2-7eed-a522-32a019057e4b","probe":"Under what clause and rule were sponsors added to public bills?","golden":"clause 7 of rule XII","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"}]},{"eval_id":"019e0524-a11c-7139-bf9b-71cd8bf76e24","probe":"Who was added as a sponsor to H.R. 247?","golden":"Ms. Omar","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. OMAR"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. OMAR"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar"}]},{"eval_id":"019e0525-2888-7fab-bbe4-24c066ee419f","probe":"Who was added as a sponsor to H.R. 31?","golden":"Mr. Stauber","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"}]},{"eval_id":"019e0529-5749-7c17-9f42-70fde0a280ae","probe":"Who was added as a sponsor to H.R. 438?","golden":"Ms. Malliotakis","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis"}]},{"eval_id":"019e0529-ab42-7f49-b945-e7fa7946e4e8","probe":"Who was added as a sponsor to H.R. 493?","golden":"Ms. DelBene","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"}]},{"eval_id":"019e053e-4d48-7017-b80c-96993dddb76d","probe":"How many patients were in the SOC alone group?","golden":"4,321","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"}]},{"eval_id":"019e053f-1f3f-7cd4-9bdf-bb8319b59261","probe":"What is the table number and title?","golden":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"}]},{"eval_id":"019e0540-facb-7b6a-8fd8-3f509341da68","probe":"What was the mean age of participants in the RECOVERY trial?","golden":"66 years","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"}]},{"eval_id":"019e0541-5acc-73a2-a0f0-4a8a3fd3f3d7","probe":"When was this table last updated?","golden":"February 29, 2024","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"}]},{"eval_id":"019e0542-7270-77f1-aa19-55066dadd841","probe":"How many patients were in the SOC alone group?","golden":"4,321","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"}]},{"eval_id":"019e0543-15cb-749c-890f-dc25b546fa1f","probe":"What percentage of participants had laboratory-confirmed SARS-CoV-2 infection?","golden":"89%","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"}]},{"eval_id":"019e0547-98af-7c91-aa30-6a7096eca524","probe":"What is the table number and title shown at the top of the page?","golden":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"}]},{"eval_id":"019e0547-eecc-7d07-95de-24c48450b6a5","probe":"On what date was this document downloaded according to the bottom of the page?","golden":"3/1/2024","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"}]},{"eval_id":"019e0549-117f-704c-b2ed-3771bcbf57de","probe":"What is the URL shown at the bottom of the page where this document was downloaded from?","golden":"https://www.covid19treatmentguidelines.nih.gov/","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"}]},{"eval_id":"019e054a-48f1-7ae1-8c9a-f98de9d0fa5b","probe":"What is the recommendation for patients hospitalized but not requiring supplemental oxygen who are at high risk of progressing to severe COVID-19?","golden":"Remdesivir","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir for immunocompromised patients; for other high-risk patients  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir for immunocompromised patients; for other high-risk patients  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir for patients who are immunocompromised; for other high-risk patients  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir for immunocompromised patients; for other high-risk patients  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir for immunocompromised patients; for other high-risk patients"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir for immunocompromised patients; for other high-risk patients"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir for immunocompromised patients; for other high-risk patients"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir for patients who are immunocompromised; for other high-risk patients"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir for patients who are immunocompromised; for other high-risk patients"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir for patients who are immunocompromised; for other high-risk patients"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised patients; (BIII) for other high-risk patients"}]},{"eval_id":"019e0550-1990-7266-9919-560f19c4cee5","probe":"In the CATCO trial, what percentage of patients received corticosteroids?","golden":"87%","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"}]},{"eval_id":"019e0550-c523-7e3c-a7bb-5e58b208e5dc","probe":"In the CATCO trial, what percentage of patients were on conventional oxygen?","golden":"54%","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"}]},{"eval_id":"019e0553-86d1-71ca-b900-5bbaabb7ca45","probe":"How many randomized controlled trials were included in the pooled analysis of individual data mentioned with ACTT-1?","golden":"9","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"}]},{"eval_id":"019e0555-7910-7ed7-a44b-456f65b6a4b0","probe":"Approximately what fraction of patients in the Solidarity trial received corticosteroids?","golden":"two-thirds","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"}]},{"eval_id":"019e055a-07af-77a5-89c9-42e3d3fa137d","probe":"What is the maximum daily dose of low-dose aspirin?","golden":"81 mg","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"}]},{"eval_id":"019e055a-a680-7323-8d08-3ac187ccf89f","probe":"What is the rating for IVIG monotherapy when glucocorticoids are contraindicated?","golden":"BIIb","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"}]},{"eval_id":"019e055d-286a-7563-a7e4-fcf6471dab8b","probe":"What is the dose of infliximab listed for intensification therapy?","golden":"5\u201310 mg/kg IV for 1 dose","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"}]},{"eval_id":"019e055e-28ea-7f76-943f-b37787cd73cb","probe":"What is the IV dose range for high-dose anakinra?","golden":"5\u201310 mg/kg/day","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"}]},{"eval_id":"019e055f-16e9-7882-9aa1-55c4030f9893","probe":"According to footnote c, in which patients should infliximab NOT be used?","golden":"patients with macrophage activation syndrome","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"}]},{"eval_id":"019e055f-c91a-7e0f-9401-67c36bb17b91","probe":"According to the Key, what does CAA stand for?","golden":"coronary artery aneurysm","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"}]},{"eval_id":"019e0561-73ca-7c46-9bf0-5c643e61cde3","probe":"What does IBW stand for according to the Key?","golden":"ideal body weight","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"}]},{"eval_id":"019e05a7-e018-7ce5-b33f-396e12ec5cd7","probe":"What is the risk level for moderately or severely immunocompromised patients regardless of vaccination status?","golden":"High","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"}]},{"eval_id":"019e05a9-4840-7d85-a06e-f789e706a095","probe":"What is the risk level for patients with mild asthma, overweight, or well-controlled diabetes?","golden":"Low","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"}]},{"eval_id":"019e05ab-8ba2-7ab7-87ce-36b3ba6a8e47","probe":"What is the risk level shown for patients with sickle cell disease or chronic kidney disease?","golden":"Intermediate","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"}]},{"eval_id":"019e05ad-fd6c-7734-88ed-1ec50c394ff9","probe":"How many conditions are listed under \"Strong or Consistent Association With Progression to Severe COVID-19\"?","golden":"8","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"}]},{"eval_id":"019e05b0-6eee-79fe-9c1a-85e69f5d1b78","probe":"What is the page number?","golden":"174","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"}]},{"eval_id":"019e05b0-9f88-7493-8093-1faf321a65c1","probe":"What is the date the document was downloaded?","golden":"3/1/2024","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"}]},{"eval_id":"019e05b0-d9cd-707e-a8fc-05816b33e002","probe":"What is the title of this section shown in the orange header?","golden":"Summary Recommendations, continued","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"}]},{"eval_id":"019e05b1-edb1-71fd-a8f1-178c8ce2372a","probe":"How many hours per day of prone ventilation does the Panel recommend?","golden":"12 to 16 hours","png_sha":"f2687af1be946044a236b7f11f8cf6f728ef1c4e9e442378d2a6ad846b6a54e4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"}]},{"eval_id":"019e05ba-b872-7e8f-9ab0-ebf540496835","probe":"How many people were in the placebo group?","golden":"761","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"}]},{"eval_id":"019e05bd-b79d-79ce-83a2-61bee82f41bd","probe":"What was the mean age of participants?","golden":"58 years","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"}]},{"eval_id":"019e05bd-fce1-7c37-9985-6a2be13c70b5","probe":"What percentage of participants received corticosteroids?","golden":"79%","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"}]},{"eval_id":"019e05bf-8d4e-7984-b130-f857ef177151","probe":"What is Pablo Tebas's financial disclosure relationship with Shionogi?","golden":"Consultant","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"}]},{"eval_id":"019e05c0-2875-7f53-8cd2-1afd5c604eef","probe":"What is Andrew T. Pavia's relationship with Haleon?","golden":"Honoraria","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"}]},{"eval_id":"019e05c1-9d7a-7ef6-8d4a-75d9a4d8bc53","probe":"What is Grant Schulert's financial disclosure relationship with Boehringer Ingelheim?","golden":"Consultant","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"}]},{"eval_id":"019e05c2-9694-7119-b6c6-e2863ab93d51","probe":"What company is Phyllis Tien disclosed as receiving research support from?","golden":"Merck","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"}]},{"eval_id":"019e05c3-4ee4-7de9-abf1-e04c45c9b57f","probe":"What is Susan Swindells's financial disclosure relationship with GSK/ViiV Healthcare?","golden":"Research support","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"}]},{"eval_id":"019e05e7-8068-7743-a656-13b1d4d4190b","probe":"How many chapter objectives are listed on this page?","golden":"5","png_sha":"4fb66d797829b4efe7d38ed6d367871d6664885f70ef83a42d3f0dfec31552e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e05e7-ce2c-772c-8efd-a4776364273c","probe":"What is the figure number for the blood pressure image?","golden":"Figure 1.0","png_sha":"4fb66d797829b4efe7d38ed6d367871d6664885f70ef83a42d3f0dfec31552e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"}]},{"eval_id":"019e05f2-f42c-7018-ab71-30b51adf12e2","probe":"What is the name of the region located between the right and left lumbar regions?","golden":"Umbilical region","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"}]},{"eval_id":"019e05f3-f4bd-74db-9544-35cd14788275","probe":"What is the name of the region directly above the umbilical region?","golden":"Epigastric region","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"}]},{"eval_id":"019e05f6-e2c6-7b53-b37c-1808bd28b0d4","probe":"What organ is shown as the example at the Organ level in the pyramid?","golden":"Bladder","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"}]},{"eval_id":"019e05f7-dd30-7195-830e-cd261e20c2b7","probe":"What organ system is shown as the example at the Organ system level?","golden":"Urinary tract system","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"}]},{"eval_id":"019e05f9-174d-779b-8451-840365bb3ab1","probe":"What type of muscle cell is shown at the Cellular level in the pyramid?","golden":"Smooth muscle cell","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"}]},{"eval_id":"019e05fa-5cd7-7bf5-ad75-0aa2f060da1e","probe":"What is the name of the plane shown at the bottom of the figure, near the body's feet?","golden":"Oblique plane","png_sha":"d0de1bb560e9b722942304e532a14882201f7692dbe44333b38e37a146f08834","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"}]},{"eval_id":"019e0a71-574c-7f62-97db-97525ad2820e","probe":"What is the figure number for the two models of atomic structure?","golden":"Figure 2.1.2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"}]},{"eval_id":"019e0a71-d77a-7463-8c88-e70ccbeb93a7","probe":"How many electrons are shown in the cloud of negative charge?","golden":"2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2 electrons"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2 electrons"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2 electrons"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2 electrons"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2 electrons"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"}]},{"eval_id":"019e0a77-521b-7c1e-96e5-0fcfd2acccfb","probe":"How many positive charges are shown in the nucleus of the electron cloud model?","golden":"2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"}]},{"eval_id":"019e0a78-60c3-7ff1-a58d-36cf79d83532","probe":"What is the pH of blood?","golden":"7.4","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"}]},{"eval_id":"019e0a78-c1e6-7be1-b2ed-7370055ce7a4","probe":"What is the pH of baking soda?","golden":"9.5","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"}]},{"eval_id":"019e0a79-38e3-7203-9d9c-b65c2c843999","probe":"What is the pH of black coffee?","golden":"5","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e0a7f-36c1-76f1-9b7d-a75d3f8b57bc","probe":"What are the regions of the enzyme called where substrates bind?","golden":"Active sites","png_sha":"56f42b1466f0ba4fd23da4bdafef8224d214d10ff10aa671d80ddc4389ea94dd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"}]},{"eval_id":"019e0a7f-f372-7caa-bdd1-9371e7bc0c6a","probe":"How many chromosomes does the page say are inside the nucleus of each cell?","golden":"46","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"}]},{"eval_id":"019e0a80-2d48-78ae-9837-df877d92d50a","probe":"Approximately how many genes do humans have in their DNA according to this page?","golden":"22,000","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000 genes"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000 genes"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"}]},{"eval_id":"019e0a80-c197-7fce-a219-ddb90e59c15f","probe":"What color represents Guanine in the diagram?","golden":"Blue","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"}]},{"eval_id":"019e0a81-1a13-7011-bf33-0b2b8c97db32","probe":"What color represents Adenine in the diagram?","golden":"Red","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"}]},{"eval_id":"019e0a82-da2f-727f-896b-27e752c2b42b","probe":"What are the two types of fatty acids labeled in the phospholipid diagram?","golden":"Saturated fatty acid and unsaturated fatty acid","png_sha":"a2c418cbcdc6704d925ad4ffdd78dee38a58fc1ea68774d0094b65c486a66bf8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and Unsaturated fatty acid"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Saturated fatty acid and unsaturated fatty acid"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"}]},{"eval_id":"019e0a83-ca15-7698-adf8-be9e8fecc270","probe":"What is labeled as the area inside the cell in the large membrane illustration?","golden":"Intracellular","png_sha":"a2c418cbcdc6704d925ad4ffdd78dee38a58fc1ea68774d0094b65c486a66bf8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"}]},{"eval_id":"019e0a8c-68fb-7f92-a952-b3faa7d123a4","probe":"What is the chapter title shown in the header at the top of the page?","golden":"Cell Membrane","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"}]},{"eval_id":"019e0a91-1c2e-7311-b881-fc5c00ce52f9","probe":"What does the arrow at the bottom of the diagram represent?","golden":"Time","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"}]},{"eval_id":"019e0a91-e6fb-79fb-b85f-ccfa87b7f449","probe":"What is labeled above the lipid bilayer in the center of the diagram?","golden":"Extracellular fluid","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"}]},{"eval_id":"019e0a92-7404-7aab-b271-b5cbb06491b3","probe":"What is labeled below the lipid bilayer in the center of the diagram?","golden":"Cytoplasm","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"}]},{"eval_id":"019e0a94-7773-7d3d-b4db-4925da2a4c81","probe":"What are the three labels above the cell images in Figure 3.1.6?","golden":"Hypertonic, Isotonic, Hypotonic","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"}]},{"eval_id":"019e0a94-dfda-768c-897f-34618204bf19","probe":"What is labeled between the two beakers in Figure 3.1.5?","golden":"Semipermeable membrane","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"}]},{"eval_id":"019e0aa6-cdb4-70a0-951f-040144680d97","probe":"What is labeled in purple at the center of the diagram?","golden":"Crystalline core","png_sha":"29f66040d5b404ad4868b569f57abcbd771a080fa8fcc185a3187093b4d3defb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"}]},{"eval_id":"019e0ab1-a72f-70b0-9619-a8e2a81fee46","probe":"What are the four nitrogenous bases listed in the legend?","golden":"Adenine, Thymine, Guanine, Cytosine","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"}]},{"eval_id":"019e0ab3-3b2c-7cf7-9e5a-87076b99eb2f","probe":"What color is used to represent Guanine in the legend?","golden":"Blue","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"}]},{"eval_id":"019e0ab4-5e27-7fa0-bdb3-55833bf40f16","probe":"What type of bonds connect the two DNA strands together according to the diagram?","golden":"Hydrogen bonds","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"}]},{"eval_id":"019e0ac7-674b-7f8f-ac85-ce02731c302a","probe":"How many stages are shown in the diagram at the top of the page?","golden":"6","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"}]},{"eval_id":"019e0ac8-36ba-7365-9435-ec92bf202c05","probe":"According to figure 3.5.3, what is the first phase of mitosis?","golden":"Prophase","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"}]},{"eval_id":"019e0ac9-ab1a-7551-88fe-ba669d0ab987","probe":"What is the last stage shown in the cell division diagram (after telophase)?","golden":"Cytokinesis","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"}]},{"eval_id":"019e0ad3-52d5-7f4c-8d3d-591d2476cefd","probe":"What is at the very top of the stem cell differentiation diagram?","golden":"Totipotent embryonic stem cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"}]},{"eval_id":"019e0adb-d424-739a-88c3-a9c6837b69aa","probe":"What type of stem cell is at the top of the diagram?","golden":"Totipotent embryonic stem cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"}]},{"eval_id":"019e0ae7-f32b-7670-af77-ced5432c5f69","probe":"What specialized cell type is shown between 'Heart muscle' and 'Skin' in the bottom row?","golden":"Red blood cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"}]},{"eval_id":"019e0b0b-0842-7562-aaee-a34590209d11","probe":"What is the figure title for Figure 4.6.2?","golden":"Development of Cancer","png_sha":"c97dbfb9dac36762398856cdab61d5779eae44284b94b744c8e56704bbf954e8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"}]},{"eval_id":"019e0b18-8c5a-7124-bb30-6bd93445411f","probe":"What does the label point to in the middle diagram?","golden":"Cell division accelerates","png_sha":"c97dbfb9dac36762398856cdab61d5779eae44284b94b744c8e56704bbf954e8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"}]},{"eval_id":"019e0b35-2b57-7c4e-9af5-fa094b59bb2c","probe":"What cell type is shown in the bottom-right image of the diagram?","golden":"Pancreatic cell","png_sha":"7b24760285552c0a3e2beb4a713373cf7079657b1996b630c4cab49bb81d2a0c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"}]},{"eval_id":"019e0eaf-c1cd-797e-834b-863d872f236e","probe":"What cell type is shown in the bottom-left image of the diagram?","golden":"Lung cell","png_sha":"7b24760285552c0a3e2beb4a713373cf7079657b1996b630c4cab49bb81d2a0c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"}]},{"eval_id":"019e0eb0-b4d4-72a3-99bd-8214864274dd","probe":"Which long bone is shown as the example in the diagram?","golden":"Femur","png_sha":"649d7b93ee3bd97ec82fa0d6dc7eb1ef1d3a531661aaf8e5a64a2e776e7befdf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"}]},{"eval_id":"019e0eb5-35af-7967-8d48-00aa0aa1a645","probe":"According to table 11.4, what is the origin of the superior oblique?","golden":"Sphenoid bone","png_sha":"e52a483f3e3402fc6874a991f546b566e2a6a0e32ba17df2ef455c46bc8e0793","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"}]},{"eval_id":"019e0eb7-fc68-7c2e-ad2c-3675d09c8aa1","probe":"What color represents the appendicular skeleton in the diagram's key?","golden":"Purple","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"}]},{"eval_id":"019e0eb9-5156-79fe-85f7-13b631e40c4d","probe":"What is the bone labeled between the Tibia and the Tarsals on the lower leg?","golden":"Fibula","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"}]},{"eval_id":"019e0eb9-c545-743f-b1c1-6053776f3ffb","probe":"What bone is labeled directly below the Humerus on the arm?","golden":"Ulna","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"}]},{"eval_id":"019e0eba-022c-7bba-8967-31ab884feb4d","probe":"What is the bone labeled directly below the Femur in the diagram?","golden":"Patella","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"}]},{"eval_id":"019e0eba-8701-7de9-8ba9-578294d6b194","probe":"What is the bone labeled directly between the Clavicle and the Thoracic cage?","golden":"Scapula","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"}]},{"eval_id":"019e0ebb-0d43-793d-85f7-7b2ed1575cdf","probe":"What is the bone labeled directly below the Radius on the arm?","golden":"Carpals","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"}]},{"eval_id":"019e0ebd-9465-739b-8454-3efaee4d4310","probe":"What is the label directly below 'Rotator brevis' in the Deep spinal muscles diagram?","golden":"Rotator longus","png_sha":"8267a338f131676cd4f156eb0c4a18c6d48352ad7a386fd12707e7503673af3f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"}]},{"eval_id":"019e0ebf-4889-76bf-9d21-fdeaa9903ac1","probe":"On the left hand side of the left lateral view, what muscle is labeled directly above the Anterior scalene?","golden":"Medial scalene","png_sha":"8267a338f131676cd4f156eb0c4a18c6d48352ad7a386fd12707e7503673af3f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"}]},{"eval_id":"019e0ec6-5ccb-7a48-a454-ea039c311db0","probe":"In the leftmost (first) stage of figure (a), what two structures are labeled?","golden":"Nucleus and Axon","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"}]},{"eval_id":"019e0ec7-9679-765e-943c-61c133fe490f","probe":"Which structure label appears in the rightmost (third) stage of figure (a)?","golden":"Node of Ranvier","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"}]},{"eval_id":"019e0eca-119a-763f-ac56-f38e33c22003","probe":"What four carpal bones are labeled in the figure 8.2.5?","golden":"Hamate, Trapezoid, Trapezium, Capitate","png_sha":"306e13b6e12dfea3dcc83ac66671b7f4f26e03a8658a38703694470c4b84acff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"}]},{"eval_id":"019e0ecd-0967-77f3-a1b2-140685a06b07","probe":"What structure is labeled at the very top of the cell?","golden":"Microvilli","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"}]},{"eval_id":"019e0ecd-62a5-7179-841c-8e4ba5c98a0a","probe":"What structure is labeled at the very bottom of the cell?","golden":"Nucleus","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"}]},{"eval_id":"019e0ece-41ab-74ba-b577-6e0aff6ee57c","probe":"What labeled structure appears between the Rough ER and the Nucleus?","golden":"Golgi apparatus","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"}]},{"eval_id":"019e0ece-aeb7-7000-b806-b1e7d144e6f6","probe":"What color is used to depict the Golgi apparatus in this figure?","golden":"orange","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"}]},{"eval_id":"019e0ed6-4075-7e2a-8d36-a54c01ef1f0a","probe":"According to the labels in the figure, which Roman numeral is assigned to the Olfactory nerve?","golden":"I","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"}]},{"eval_id":"019e0ed6-d0db-7047-a35c-28a5f0394d4e","probe":"How many cranial nerves are labeled in this figure?","golden":"12","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"}]},{"eval_id":"019e0ed7-29c1-7353-a0d0-78dc86f5bf0d","probe":"Which cranial nerve is labeled with the Roman numeral X?","golden":"Vagus nerve","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"}]},{"eval_id":"019e0ed7-a580-70c5-9af2-82e1e6d3b27c","probe":"Which cranial nerve is labeled directly above the Trochlear nerve on the left side of the figure?","golden":"Oculomotor nerve","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"}]},{"eval_id":"019e0ed8-e384-740f-8339-b731e7477bd0","probe":"Which Roman numeral is assigned to the Trigeminal nerve?","golden":"V","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"}]},{"eval_id":"019e0edf-b3c8-7227-995d-59d8e7337a13","probe":"What is the membrane potential value at the dashed horizontal line labeled \"Threshold\"?","golden":"-55 mV","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"}]},{"eval_id":"019e0ee0-04e8-7f4f-a3d3-f732f8ce4367","probe":"What does the x-axis represent?","golden":"Time","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"}]},{"eval_id":"019e0ee2-00eb-788b-982a-17e9bbe92888","probe":"How many separate cross-section illustrations are shown in Figure 14.1.1","golden":"3","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"}]},{"eval_id":"019e0ee4-1b7c-773f-963c-fc9c8846cdc2","probe":"In the rightmost (third) illustration of Figure 14.1.1, what label appears at the far right?","golden":"Ectoderm","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"}]},{"eval_id":"019e0ee5-7413-77ac-928e-9349a0add2e3","probe":"In the far-left illustration of Figure 14.1.1, what word is labeled at the end of the curved arrow?","golden":"Convergence","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"}]},{"eval_id":"019e0ee7-d44b-7f7f-9dde-44db50c5a6d7","probe":"In panel (a), what label is shown at the top-left of the panel?","golden":"Resting muscle","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"}]},{"eval_id":"019e0ee8-0c80-7766-bb63-e01a6477af62","probe":"In panel (a), what label is shown at the top-right of the panel?","golden":"Active muscle","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"}]},{"eval_id":"019e0ee8-b795-7df0-985e-b6a23bc84e11","probe":"In panel (b), what process is shown at the top-right when oxygen is present?","golden":"Aerobic respiration","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"}]},{"eval_id":"019e0ee9-027b-7c34-9c19-e3a9f92ddc36","probe":"In panel (b), what is produced when there is no oxygen?","golden":"Lactic acid","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid to blood  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid to blood"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"}]},{"eval_id":"019e0ee9-9d8a-74f4-a4d4-fdae97459d0d","probe":"In panel (c), what three substances flow INTO the cellular respiration mitochondria?","golden":"Blood glucose, Pyruvic acid, Fatty acids","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"}]},{"eval_id":"019e0eee-1192-75e7-bc00-9eba77492379","probe":"In Figure 17.5.2, what does step 1 say?","golden":"Blood calcium concentration drops","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"}]},{"eval_id":"019e0eee-6b0f-7623-9bf9-f65dcda769bd","probe":"In Figure 17.5.2, what does step 4 say?","golden":"Blood calcium levels increase","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"}]},{"eval_id":"019e0ef0-10bf-71af-9ca6-cd2d668f1d1c","probe":"In Figure 17.5.2, what does step 6 describe the effects of?","golden":"calcitonin on bone","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"}]},{"eval_id":"019e0ef1-0b05-7277-bad0-8b16372f30ef","probe":"In Figure 17.5.2, what is the title of item 3b?","golden":"Effects of PTH on kidneys","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"}]}]},{"summary":{"model":"grok_4_3","name":"Grok 4.3","total_evals":550,"total_cells":16500,"l2_cells":14198,"l3_cells":1768,"l4_cells":534,"acceptable":96.76,"runs":30,"partial":false,"l2_evals":433,"l3_evals":76,"l4_evals":41},"evals":[{"eval_id":"019dfb49-c621-751e-8311-221426895f61","probe":"What date does the fiscal year end?","golden":"June 30, 2013","png_sha":"e78f4e20277a031b7f8a1c8ec01e35359d5db802026c772a280aa46b2e15036d","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"June 30\n"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"June 30\n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"June 30\n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"June 30\n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"June 30\n"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"June 30"}]},{"eval_id":"019dfafb-dcbb-70a3-96b4-fcb14e3ee61c","probe":"What was the cost of revenues for 2023?","golden":"$133,332 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"133,332\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"133,332\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"133332\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"133332\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"$133,332"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"$133,332"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"133,332"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":26,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$133,332 (millions)"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"133332"}]},{"eval_id":"019dfb0e-aa32-78f0-b197-81311a562d15","probe":"What were the total long-lived assets in the United States as of March 31, 2025?","golden":"$149,304 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"149304\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304\n"},{"run_index":3,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$149,304 (in millions)\n"},{"run_index":4,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$149,304 (in millions)\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"},{"run_index":6,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$149,304 (in millions)"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"$149,304"},{"run_index":9,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$149,304 (in millions)"},{"run_index":10,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$149,304 (in millions)"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"$149,304"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"$149,304"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"},{"run_index":16,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$149,304 (in millions)"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"$149,304"},{"run_index":18,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$149,304 (in millions)"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"},{"run_index":22,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$149,304 (in millions)"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"},{"run_index":24,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$149,304 (in millions)"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"$149,304"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"149304"}]},{"eval_id":"019dfb20-e27a-7c39-b2f6-4f9d7929ea4e","probe":"What is the estimated fair value of total fixed maturity securities AFS as of December 31, 2022?","golden":"$276,780 million","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":4,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)\n"},{"run_index":1,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)\n"},{"run_index":2,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)\n"},{"run_index":3,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)\n"},{"run_index":4,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"$276,780"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"$ 276,780"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"$276,780"},{"run_index":8,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"$276,780"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"$276,780"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"$276,780"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"$276,780"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"$276,780"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"276780"},{"run_index":15,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"$276,780"},{"run_index":17,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)"},{"run_index":18,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"$276,780"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"276780"},{"run_index":21,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"$276,780"},{"run_index":23,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)"},{"run_index":24,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"$276,780"},{"run_index":26,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)"},{"run_index":27,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"$276,780"},{"run_index":29,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$276,780 (in millions)"}]},{"eval_id":"019dfb22-9390-7dca-91a4-198eb5ec30b4","probe":"What is the amortized cost net of ACL for Baa rated securities as of December 31, 2022?","golden":"$81,280 million","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"81280\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"81280\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"81280\n"},{"run_index":3,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$81,280 (in millions)\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"81280\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"$81,280"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"$81,280"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"$81,280"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"$81,280"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"81,280"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"$81,280"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"81280"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"$81,280"}]},{"eval_id":"019de200-d499-74c0-a9b3-74b464fcf74b","probe":"What is the color name listed for the carpet base?","golden":"503 Ginger","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Ginger\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Ginger"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"}]},{"eval_id":"019de200-d4a0-7403-856e-aa22d2bdae81","probe":"What is the name of the company shown at the top of the page?","golden":"Acceleron Pharma Inc.","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong spelling","answer":"Accelron Pharma Inc.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":7,"verdict":4,"source":"human","note":"wrong spelling","answer":"Accelero Pharma Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":12,"verdict":4,"source":"human","note":"wrong spelling","answer":"Accelron Pharma Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."}]},{"eval_id":"019de200-d4a4-7cca-a0e9-a3ce81d8b684","probe":"What is the federal income tax expense at the statutory rate for 2015?","golden":"34.0%","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%\n"},{"run_index":2,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found\n"},{"run_index":3,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":8,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":11,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":18,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":19,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":28,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":29,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"}]},{"eval_id":"019de200-d4ea-7529-926e-f6d2957fdefe","probe":"Who is the Named Tenant?","golden":"2U Harkins Road LLC","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC, a Delaware limited liability company\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company\n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC, a Delaware limited liability company\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company\n"},{"run_index":5,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC, a Delaware limited liability company"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":7,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC, a Delaware limited liability company"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":10,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC, a Delaware limited liability company"},{"run_index":11,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC, a Delaware limited liability company"},{"run_index":12,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC, a Delaware limited liability company"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":14,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC, a Delaware limited liability company"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":16,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC, a Delaware limited liability company"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":21,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC (Delaware LLC)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":23,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC, a Delaware limited liability company"},{"run_index":24,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC, a Delaware limited liability company"},{"run_index":28,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC, a Delaware limited liability company"},{"run_index":29,"verdict":4,"source":"human","note":"wrong spelling","answer":"2U Haskins Road LLC, a Delaware limited liability company"}]},{"eval_id":"019dfaf8-7549-77d5-b050-b8468d035af7","probe":"What was the total amount of Class C share repurchases for the three months ended March 31, 2025?","golden":"$12,535 million","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million\n"},{"run_index":2,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$12,535 (in millions)\n"},{"run_index":3,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$12,535 (millions)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million\n"},{"run_index":5,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$12,535 (millions)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":11,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$12,535 (millions)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":16,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$12,535 (millions)"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"12,535"},{"run_index":18,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$12,535 (in millions)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":21,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$12,535 (millions)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":24,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$12,535 (millions)"},{"run_index":25,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$12,535 (in millions)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"}]},{"eval_id":"019dfafb-3912-792d-bc47-54ca00054b5c","probe":"What were the revenues for 2025?","golden":"$402,836 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":20,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$402,836 (millions)"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"$ 402,836"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"$ 402,836"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":27,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$402,836 (millions)"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"$402,836"}]},{"eval_id":"019dfafb-834e-72a8-893b-436ffbf094a2","probe":"What was the net income for 2024?","golden":"$100,118 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118\n"},{"run_index":3,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$100,118 (millions)\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":7,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$100,118 (in millions)"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":14,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$100,118 (millions)"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"$100,118"}]},{"eval_id":"019dfafc-94fe-761b-9254-9f753ab96d14","probe":"What was the total amount of share repurchases for the nine months ended September 30, 2025?","golden":"$40,117 million","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.1 billion (or $40,117 million)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million (or $40.1 billion)  \n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.1 billion ($40,117 million)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.1 billion ($40,117 million)"},{"run_index":6,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":7,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":9,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":10,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":11,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":12,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":13,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":14,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.1 billion (or $40,117 million)"},{"run_index":16,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":18,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":20,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":21,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":22,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":23,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":24,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":25,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":26,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":27,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":29,"verdict":4,"source":"human","note":"magnitude","answer":"$40.1 billion"}]},{"eval_id":"019dfb0e-3ccc-74fa-9d0d-91c2663bea11","probe":"What was the total revenue for the three months ended March 31, 2025?","golden":"$90,234 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":4,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$90,234 (in millions)\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"90234\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million\n"},{"run_index":3,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$90,234 (in millions)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"$90,234"},{"run_index":6,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$90,234 (in millions)"},{"run_index":7,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$90,234 (in millions)"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"90234"},{"run_index":9,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$90,234 (in millions)"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"$90,234"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"90234"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"$90,234"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"90234"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"90234"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"$90,234"},{"run_index":16,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$90,234 (in millions)"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"$90,234"},{"run_index":18,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$90,234 (in millions)"},{"run_index":19,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"** $90,234 (in millions)\n\n**"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"$90,234"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"$90,234"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":23,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$90,234 (in millions)"},{"run_index":24,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$90,234 (millions)"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"90234"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"$90,234"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"90234"},{"run_index":28,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$90,234 (in millions)"},{"run_index":29,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"90234 (in millions)"}]},{"eval_id":"019dfb0f-11dc-7143-87ab-1b18f0a0c5b8","probe":"What was Google Cloud's operating income for the three months ended March 31, 2025?","golden":"$2,177 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million\n\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$2,177\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million\n"},{"run_index":5,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$2,177 (in millions)"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"$2,177"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"2,177"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"$2,177"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"$2,177"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"$2,177"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"$2,177"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":23,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"2177 (in millions)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"$2,177"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"$2,177"}]},{"eval_id":"019dfb10-1fb2-7986-b06c-55501bbd796e","probe":"What was the United States revenue for the three months ended September 30, 2025?","golden":"$48,758 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$ 48,758\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"$48,758"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"$48,758"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"$48,758"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"48758"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"$48,758"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"$48,758"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"$48,758"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"$48,758"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"$48,758"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"$48,758"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"$48,758"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"}]},{"eval_id":"019dfb10-c712-7d30-9f15-c857b9160151","probe":"What was the EMEA revenue for the nine months ended September 30, 2025?","golden":"$84,096 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096\n"},{"run_index":1,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$84,096 (in millions)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"84,096\n"},{"run_index":4,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"84,096 (in millions)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"$84,096"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"84096"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"84096"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":15,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"84096 (in millions)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"84096"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"84096"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"84096"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"$84,096"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"84096"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"$84,096"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"84,096"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"}]},{"eval_id":"019dfb11-2196-7673-aeb2-eebcf53e53b2","probe":"What was the APAC revenue for the three months ended September 30, 2024?","golden":"$14,547 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$14,547\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$14,547\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$14,547\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"14,547\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":8,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$14,547 (millions)"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"14547"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"14547"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"14547"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":19,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":20,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$14,547 (millions)"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"14547"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"14547"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"14,547"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"$14,547"}]},{"eval_id":"019dfb11-8ce1-72d9-b0ab-fc0be563e187","probe":"What were the total revenues for the nine months ended September 30, 2025?","golden":"$289,007 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"$289,007"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"$289,007"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"$289,007"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"$ 289,007"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"$ 289,007"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"$ 289,007"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"$ 289,007"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million"}]},{"eval_id":"019dfb25-429c-7aee-a55e-43ed0574b742","probe":"What is the estimated fair value of policyholder account balances?","golden":"$115,408 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$115,408 million\n"},{"run_index":2,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014\n"},{"run_index":3,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"115408 (in millions)\n"},{"run_index":4,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014\n"},{"run_index":5,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"115408 (in millions)"},{"run_index":6,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"115408"},{"run_index":8,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":9,"verdict":4,"source":"precedent","note":"magnitude","answer":"115408"},{"run_index":10,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014"},{"run_index":11,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"$115,408"},{"run_index":13,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":14,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":15,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014"},{"run_index":16,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"115408"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"$115,408"},{"run_index":19,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014"},{"run_index":20,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014"},{"run_index":21,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014"},{"run_index":22,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014"},{"run_index":23,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014"},{"run_index":24,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":25,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014"},{"run_index":26,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014 (dash)"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"115408"},{"run_index":28,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014"},{"run_index":29,"verdict":4,"source":"human","note":"extraction failure","answer":"\u2014"}]},{"eval_id":"019dfb25-8392-72a3-af31-c1805d75def2","probe":"What is the estimated fair value of equity securities?","golden":"$1,684 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million\n"},{"run_index":1,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"1,684 (in millions)\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"1684\n"},{"run_index":3,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"1,684 (in millions)\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"1,684\n"},{"run_index":5,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"1,684 (in millions)"},{"run_index":6,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"1,684 (in millions)"},{"run_index":7,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"1684 (in millions)"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":13,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$1,684 (in millions)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":19,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"1,684 (in millions)"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"1,684"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"}]},{"eval_id":"019dfb26-154c-7462-80c9-ac925ac520e6","probe":"What is the notional amount of foreign currency swaps?","golden":"$56,025 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$56,025\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$56,025\n"},{"run_index":2,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$56,025 (in millions)\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$56,025\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$56,025\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"},{"run_index":7,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$56,025 (in millions)"},{"run_index":8,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$56,025 (in millions)"},{"run_index":9,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$56,025 (in millions)"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"56025"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"},{"run_index":13,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$56,025 (in millions)"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"56025"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"},{"run_index":18,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$56,025 (in millions)"},{"run_index":19,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$56,025 (in millions)"},{"run_index":20,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$56,025 (in millions)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$56,025 million"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"},{"run_index":23,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"},{"run_index":24,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$56,025 (in millions)"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"},{"run_index":28,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$56,025 (in millions)"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"$56,025"}]},{"eval_id":"019dfb45-009b-71c5-a560-66fa6f28c0b7","probe":"What were the personal income taxes for 2024?","golden":"$116.5 billion","png_sha":"be9e4b96b82c2251ae314ddc72ad643547069399fbff67cb23663b4b60410b07","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"116.5\n"},{"run_index":1,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)\n"},{"run_index":2,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"116.5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"116.5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":9,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)"},{"run_index":10,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":12,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)"},{"run_index":13,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)"},{"run_index":14,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"116.5"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"116.5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":18,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":20,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)"},{"run_index":21,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)"},{"run_index":22,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)"},{"run_index":23,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)"},{"run_index":24,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"116.5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"116.5"},{"run_index":29,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"116.5 (billions)"}]},{"eval_id":"019dfffa-4c63-71d9-9bae-44bb0f5d067a","probe":"What is the total primary government amount due to component units?","golden":"$209,125","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209125\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209125\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209125\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209125"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"13 (in thousands)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209125"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209125"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 (in thousands)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209125"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209125"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 (in thousands)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209125"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$209,125 (in thousands)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209125"}]},{"eval_id":"019e000b-683c-7e54-aaf2-3d634ac03517","probe":"What is the total expenses for Education in Graph MDA-5?","golden":"$46,073 million","png_sha":"3f8e2c78a2134ddb79f740cc731c989a29e5b11d89cdb0254e1f1740d44cfdb0","worst":4,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$46,073 (in millions)\n"},{"run_index":1,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$46,073 (in millions)\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073\n"},{"run_index":4,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$46,073 (millions)\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":6,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":7,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":8,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":9,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$46,073 (in millions)"},{"run_index":10,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":11,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":12,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":13,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":14,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":15,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":16,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":17,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":18,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":19,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$46,073 (millions)"},{"run_index":20,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":21,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":22,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":24,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":25,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":26,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":27,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":28,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"},{"run_index":29,"verdict":4,"source":"precedent","note":"magnitude","answer":"$46,073"}]},{"eval_id":"019e0082-3d98-723b-b6b4-132e744dab15","probe":"Which county is labeled at the bottom-right area of the map, below Ellis?","golden":"Navarro","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"JOHNSON\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":7,"verdict":4,"source":"precedent","note":"wrong value","answer":"JOHNSON"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAVARRO"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro**  \n**"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAVARRO"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAVARRO"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAVARRO"}]},{"eval_id":"019e00a1-03cf-7de0-9353-8ede1f29d21e","probe":"What time did the House meet?","golden":"10 a.m.","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.  \n"},{"run_index":1,"verdict":4,"source":"human","note":"extraction failure","answer":"The Ho"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."}]},{"eval_id":"019e00ac-a893-7e85-9fc2-0de0e7d020dd","probe":"Did Cherfilus-McCormick vote yea or nay?","golden":"nay","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":6,"verdict":4,"source":"precedent","note":"wrong category","answer":"yea"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"}]},{"eval_id":"019e00ac-faaf-7e38-b571-92ff92b76932","probe":"Garcia of California voted in which column?","golden":"NAYS","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found\n"},{"run_index":1,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS (yes column)\n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS\n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS\n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS (yes)  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS\u2014204"},{"run_index":7,"verdict":4,"source":"human","note":"wrong category","answer":"YEA"},{"run_index":8,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":9,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS\u2014214"},{"run_index":10,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":11,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS (214)"},{"run_index":12,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS\u2014214"},{"run_index":13,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS (214)"},{"run_index":14,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS (YEA\u2014214 column)"},{"run_index":15,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS column (yes vote)"},{"run_index":16,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":17,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":18,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":19,"verdict":4,"source":"precedent","note":"unwarranted abstention","answer":"not found"},{"run_index":20,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":21,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS (YEA column)"},{"run_index":22,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":23,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":24,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":25,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":26,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":27,"verdict":4,"source":"human","note":"wrong category","answer":"YEAS column"},{"run_index":28,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"},{"run_index":29,"verdict":4,"source":"precedent","note":"wrong category","answer":"YEAS"}]},{"eval_id":"019e00ad-32af-76df-9057-a199ce91dd17","probe":"How many \"Garcia\" members are listed in the NAYS column?","golden":"3","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":1,"verdict":4,"source":"human","note":"wrong count","answer":"0\n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"2\n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"0\n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"0\n"},{"run_index":5,"verdict":4,"source":"precedent","note":"wrong count","answer":"2"},{"run_index":6,"verdict":4,"source":"precedent","note":"wrong count","answer":"2"},{"run_index":7,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":8,"verdict":4,"source":"precedent","note":"wrong count","answer":"2"},{"run_index":9,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":10,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":11,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":12,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":13,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":14,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":15,"verdict":4,"source":"precedent","note":"wrong count","answer":"2"},{"run_index":16,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":17,"verdict":4,"source":"precedent","note":"wrong count","answer":"2"},{"run_index":18,"verdict":4,"source":"precedent","note":"wrong count","answer":"2"},{"run_index":19,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":20,"verdict":4,"source":"precedent","note":"wrong count","answer":"2"},{"run_index":21,"verdict":4,"source":"precedent","note":"wrong count","answer":"2"},{"run_index":22,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":23,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":24,"verdict":4,"source":"precedent","note":"wrong count","answer":"2"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":26,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":27,"verdict":4,"source":"human","note":"wrong count","answer":"0"},{"run_index":28,"verdict":4,"source":"human","note":"wrong count","answer":"0**  \n**"},{"run_index":29,"verdict":4,"source":"human","note":"wrong count","answer":"0"}]},{"eval_id":"019e00ae-10e5-7c6b-956c-c30654f0adda","probe":"What is the last name listed in the YEAS column?","golden":"Zinke","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":7,"verdict":4,"source":"precedent","note":"wrong value","answer":"Wilson (FL)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":9,"verdict":4,"source":"precedent","note":"wrong value","answer":"Wilson (FL)"},{"run_index":10,"verdict":4,"source":"precedent","note":"wrong value","answer":"Wilson (FL)"},{"run_index":11,"verdict":4,"source":"precedent","note":"wrong value","answer":"Wilson (FL)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":19,"verdict":4,"source":"precedent","note":"wrong value","answer":"Wilson (FL)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":21,"verdict":4,"source":"precedent","note":"wrong value","answer":"Wilson (FL)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":23,"verdict":4,"source":"precedent","note":"wrong value","answer":"Wilson (FL)"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Quigley"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"},{"run_index":27,"verdict":4,"source":"precedent","note":"wrong value","answer":"Wilson (FL)"},{"run_index":28,"verdict":4,"source":"precedent","note":"wrong value","answer":"Wilson (FL)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke"}]},{"eval_id":"019e0524-a11c-7139-bf9b-71cd8bf76e24","probe":"Who was added as a sponsor to H.R. 247?","golden":"Ms. Omar","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR\n"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR\n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. STAUBER\n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. STAUBER\n"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. STAUBER\n"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. OMAR"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. OMAR"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. STAUBER"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. STAUBER"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. OMAR"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. OMAR"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. OMAR"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. STAUBER"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. OMAR"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. STAUBER"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. OMAR"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. STAUBER"}]},{"eval_id":"019e0529-5749-7c17-9f42-70fde0a280ae","probe":"Who was added as a sponsor to H.R. 438?","golden":"Ms. Malliotakis","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS\n"},{"run_index":3,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS\n"},{"run_index":5,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":8,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":12,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":18,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":22,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":26,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS"}]},{"eval_id":"019e0529-ab42-7f49-b945-e7fa7946e4e8","probe":"Who was added as a sponsor to H.R. 493?","golden":"Ms. DelBene","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":19,"verdict":4,"source":"precedent","note":"unwarranted abstention","answer":"not found"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE"}]},{"eval_id":"019e05a7-e018-7ce5-b33f-396e12ec5cd7","probe":"What is the risk level for moderately or severely immunocompromised patients regardless of vaccination status?","golden":"High","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":10,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High**  \n**"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":18,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High**  \n**"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"}]},{"eval_id":"019e0a91-1c2e-7311-b881-fc5c00ce52f9","probe":"What does the arrow at the bottom of the diagram represent?","golden":"Time","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"extraction failure","answer":"The ar"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (diffusion over time)  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (showing diffusion process)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (diffusion direction)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"progression of time (showing diffusion)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (diffusion progress)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (direction)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (diffusion process)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (as diffusion occurs)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the passage of time (showing diffusion progress)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (left to right)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (diffusion progression)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (showing diffusion process)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"progression of time (left to right)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (as diffusion occurs)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"progression of time (molecules diffusing)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"progression of time (diffusion over time)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (diffusion over time)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (diffusion process)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"progression of time (during diffusion)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (diffusion process)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"progression of time (diffusion occurring)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (showing diffusion process)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"progression of time (simple diffusion)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (as diffusion occurs)**  \n**"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (showing diffusion)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"progression of time (diffusion over time)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"progression of time (during diffusion)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (during diffusion)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"passage of time (left to right)"}]},{"eval_id":"019e0a94-dfda-768c-897f-34618204bf19","probe":"What is labeled between the two beakers in Figure 3.1.5?","golden":"Semipermeable membrane","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong spelling","answer":"Semimpermeable membrane\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong spelling","answer":"Semimpermeable membrane\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":10,"verdict":4,"source":"human","note":"wrong spelling","answer":"Semimpermeable membrane"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane**  \n**"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"}]},{"eval_id":"019e0eb9-5156-79fe-85f7-13b631e40c4d","probe":"What is the bone labeled between the Tibia and the Tarsals on the lower leg?","golden":"Fibula","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fibula\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":11,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":13,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula**  \n**"},{"run_index":17,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":18,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":19,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula**  \n**"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":27,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"}]},{"eval_id":"019e0ebb-0d43-793d-85f7-7b2ed1575cdf","probe":"What is the bone labeled directly below the Radius on the arm?","golden":"Carpals","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals**  \n**"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals**  \n**"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals**  \n**"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals**  \n**"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals**  \n**"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":22,"verdict":4,"source":"precedent","note":"wrong label","answer":"Ulna"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals**  \n**"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals"}]},{"eval_id":"019e0ec7-9679-765e-943c-61c133fe490f","probe":"Which structure label appears in the rightmost (third) stage of figure (a)?","golden":"Node of Ranvier","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong label","answer":"Myelin\n"},{"run_index":1,"verdict":4,"source":"human","note":"wrong label","answer":"Myelin**  \n**"},{"run_index":2,"verdict":4,"source":"human","note":"wrong label","answer":"Myelin\n"},{"run_index":3,"verdict":4,"source":"human","note":"wrong label","answer":"Myelin**  \n**"},{"run_index":4,"verdict":4,"source":"human","note":"wrong label","answer":"Myelin**  \n**"},{"run_index":5,"verdict":4,"source":"human","note":"wrong label","answer":"Myelin**\n\n**"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Myelin (or Node of Ranvier)"},{"run_index":7,"verdict":4,"source":"precedent","note":"wrong label","answer":"Myelin"},{"run_index":8,"verdict":4,"source":"precedent","note":"wrong label","answer":"Myelin"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Myelin (also Node of Ranvier)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Myelin (also Node of Ranvier)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Myelin (or Node of Ranvier)**  \n**"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Myelin (also Node of Ranvier)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":14,"verdict":4,"source":"precedent","note":"wrong label","answer":"Myelin"},{"run_index":15,"verdict":4,"source":"precedent","note":"wrong label","answer":"Myelin"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Myelin (also Node of Ranvier)**  \n**"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Myelin (or Node of Ranvier)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Myelin (and Node of Ranvier)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Myelin (or Node of Ranvier)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier (also Myelin)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Myelin (or Node of Ranvier)"},{"run_index":22,"verdict":4,"source":"precedent","note":"wrong label","answer":"Myelin"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Myelin (or Node of Ranvier)"},{"run_index":24,"verdict":4,"source":"human","note":"wrong label","answer":"Myelin**  \n**"},{"run_index":25,"verdict":4,"source":"human","note":"wrong label","answer":"Myelin**  \n**"},{"run_index":26,"verdict":4,"source":"precedent","note":"wrong label","answer":"Myelin"},{"run_index":27,"verdict":4,"source":"human","note":"wrong label","answer":"Myelin**  \n**"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Myelin (or Node of Ranvier)"},{"run_index":29,"verdict":4,"source":"precedent","note":"wrong label","answer":"Myelin"}]},{"eval_id":"019e0edf-b3c8-7227-995d-59d8e7337a13","probe":"What is the membrane potential value at the dashed horizontal line labeled \"Threshold\"?","golden":"-55 mV","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV**  \n**"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV\n"},{"run_index":4,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":7,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV**  \n**"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":14,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"\u221255 mV"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":22,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":25,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":26,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"-55 mV"}]},{"eval_id":"019de200-d496-74b2-a2cc-5c7a6982836d","probe":"What is the Tenant Notice Address suite number?","golden":"Suite 900","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"900"}]},{"eval_id":"019de200-d4d3-7a72-9dfe-0011bce8efc8","probe":"What is the maximum tenant improvement allowance amount in dollars?","golden":"$559,160.00","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160\n"},{"run_index":5,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":7,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":8,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":10,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":12,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":13,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":18,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":20,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":23,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":24,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":27,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"},{"run_index":29,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"559160"}]},{"eval_id":"019de200-d4ef-7bf8-a7ba-27307744e3f9","probe":"What is the 2nd Floor Build-Out Allowance amount?","golden":"$600,000.00","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"$600,000\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"$600,000\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"$600,000\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"$600,000\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"$600,000\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"$600,000"}]},{"eval_id":"019de200-d505-7a87-bf67-4ac7fc6b2fd3","probe":"How many days before policy expiration must original copies of policies be delivered to Landlord?","golden":"fifteen (15) days","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"15 days\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"}]},{"eval_id":"019de200-d508-7af1-93e1-8436c404657e","probe":"How many business days in advance must Tenant provide the Notice of Permitted Transfer?","golden":"10 Business Days","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"10"}]},{"eval_id":"019de200-d515-7626-bd30-2e0c3b0c3b7f","probe":"Within how many Business Days must Borrower pay any excess if it results from a reserve against the Borrowing Base?","golden":"five (5) Business Days","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019de200-d523-7d03-9cf0-aa0eb615e454","probe":"Within how many calendar days following lease termination must Lessor conduct and deliver the Phase I environmental assessment under section 11.4?","golden":"fifteen (15) calendar days","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"15 calendar days"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"15"}]},{"eval_id":"019de200-d525-7710-85f5-fc41b54afbb0","probe":"Within how many calendar days must Lessee deliver a signed counterpart of the sublease agreement to Lessor after its execution?","golden":"five (5) calendar days","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019de740-e7d8-75d0-835d-3a79745c66cc","probe":"How many consecutive Business Days after Landlord's receipt of the Untenantability Notice are required (in non-Force Majeure cases)?","golden":"five (5)","png_sha":"658d8ecfa29b1c0cf9870b2d1c622a5cff7347859e7674b418cc4660be4eb7b9","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019dfb3f-d06a-7547-a4b6-8a6e4c150c61","probe":"What is the suite number of the office address listed at the bottom of the letter?","golden":"Suite 1850","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1850"}]},{"eval_id":"019dffff-131f-7d34-8e0c-2be25da41c0d","probe":"What two courts are shown at the bottom level under County-Level Courts?","golden":"Municipal Courts and Justice of the Peace Courts","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*\n"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*\n"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*\n"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*\n"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":6,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":7,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":8,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":9,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":10,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":11,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":12,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":13,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":14,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":15,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":16,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":17,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":18,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":19,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":20,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":21,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":22,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":23,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":24,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":25,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":26,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":27,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":28,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"},{"run_index":29,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*"}]},{"eval_id":"019e0005-d4aa-7f1f-8391-f99f6caf3697","probe":"How many City Council Members are from Brooklyn?","golden":"16 Members","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"16"}]},{"eval_id":"019e0006-0655-7fe4-88c4-d697fbcb759a","probe":"How many Council Members does Queens have?","golden":"14 Members","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"14"}]},{"eval_id":"019e002a-8546-75d0-9290-e4f34687786f","probe":"What year ended is referenced at the top of the page?","golden":"December 31, 2024","png_sha":"4ceaa28bf7551920a1890b7fbf19a27b1cc875ad22828548d20d5021ffb4cb9e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"2024\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"2024\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"2024\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"2024\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"2024\n"},{"run_index":5,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"2024 (December 31)"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"2024"}]},{"eval_id":"019e0081-be2e-71be-9017-964db6e9e08a","probe":"What is the maximum value shown on the map's mile scale bar?","golden":"45 Miles","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"45"}]},{"eval_id":"019e0085-cd0d-7043-93eb-a33714bb645a","probe":"What GASB Statement number did the Council adopt in fiscal year 2024?","golden":"No. 96","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"96"}]},{"eval_id":"019e00ad-aa7b-733c-8e2b-33b7f30d7cfc","probe":"Did Senator Whittaker appear on this vote?","golden":"No, Whittaker is not listed on this page","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"No\n"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":6,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":7,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":8,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":9,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":10,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":11,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":12,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":13,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":14,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":15,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":16,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":17,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":18,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":19,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":20,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":21,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":22,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":23,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":24,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":25,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":26,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":27,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":28,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"},{"run_index":29,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"not found"}]},{"eval_id":"019e00af-5886-7c0c-acb0-3467635835d6","probe":"What time did the recorded vote take place (the \u25a1 time stamp before the McGOVERN demand)?","golden":"1:56 PM (1356)","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"1:56 p.m. (\u25a1 1356)\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"1356 (1:56 p.m.)\n\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"\u25a1 1356"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":16,"verdict":3,"source":"human","note":"answer expanded","answer":"1:56 p.m. (\u25a1 1356)"},{"run_index":17,"verdict":3,"source":"human","note":"answer expanded","answer":"1:56 p.m. (\u25a1 1356)"},{"run_index":18,"verdict":3,"source":"human","note":"answer compressed","answer":"\u25a1 1356"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":21,"verdict":3,"source":"human","note":"answer expanded","answer":"1:56 p.m. (\u25a1 1356)"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":26,"verdict":3,"source":"human","note":"answer expanded","answer":"1:56 p.m. (\u25a1 1356)"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1356"},{"run_index":29,"verdict":3,"source":"human","note":"answer expanded","answer":"1:56 p.m. (\u25a1 1356)"}]},{"eval_id":"019e00af-a493-76fe-9fc1-0e6baa42ab53","probe":"What time did the House return from recess (the \u25a1 time stamp before \"AFTER RECESS\")?","golden":"1:30 PM (1330)","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"1330 (1:30 p.m.)\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"1330"}]},{"eval_id":"019e00b0-60e7-7eb0-ace3-4de6646279c2","probe":"Which members changed their vote from \"yea\" to \"nay\"?","golden":"Ms. Ross, Mrs. Foushee, Mr. Raskin, and Mr. Krishnamoorthi","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI\n"},{"run_index":1,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI\n"},{"run_index":2,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, Krishnamoorthi\n"},{"run_index":3,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI\n\n"},{"run_index":4,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":6,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":7,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":8,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":9,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":10,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, Krishnamoorthi"},{"run_index":11,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":12,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":13,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":14,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, Krishnamoorthi"},{"run_index":15,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, Krishnamoorthi"},{"run_index":16,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":17,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, Krishnamoorthi"},{"run_index":18,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, Krishnamoorthi"},{"run_index":19,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":20,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":21,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, Krishnamoorthi"},{"run_index":22,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":23,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":24,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, Krishnamoorthi"},{"run_index":25,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, Krishnamoorthi"},{"run_index":26,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":27,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin, Krishnamoorthi"},{"run_index":28,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":29,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"}]},{"eval_id":"019e051b-f048-7557-907e-87bf1f5319e0","probe":"What was the rollcall vote number for the Driscoll nomination?","golden":"Rollcall Vote No. 90 Ex.","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90 Ex. \n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90 Ex."},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"90"}]},{"eval_id":"019e051f-e004-7dd8-b253-949abd5846ae","probe":"Who is Jess Andrews leaving to work for, according to Senator Kennedy's tribute?","golden":"the new Senator from Ohio","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (deputy chief of staff)\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (deputy chief of staff)\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)  \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"article handling","answer":"our new Senator from Ohio"},{"run_index":6,"verdict":3,"source":"human","note":"article handling","answer":"new Senator from Ohio"},{"run_index":7,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (deputy chief of staff)"},{"run_index":8,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)"},{"run_index":9,"verdict":3,"source":"human","note":"article handling","answer":"new Senator from Ohio"},{"run_index":10,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (deputy chief of staff)"},{"run_index":11,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (deputy chief of staff)"},{"run_index":12,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)"},{"run_index":13,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)"},{"run_index":14,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)"},{"run_index":15,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (deputy chief of staff)"},{"run_index":16,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)"},{"run_index":17,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)"},{"run_index":18,"verdict":3,"source":"human","note":"article handling","answer":"new Senator from Ohio"},{"run_index":19,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)"},{"run_index":20,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)"},{"run_index":21,"verdict":3,"source":"human","note":"article handling","answer":"new Senator from Ohio"},{"run_index":22,"verdict":3,"source":"human","note":"article handling","answer":"new Senator from Ohio"},{"run_index":23,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)"},{"run_index":24,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (deputy chief of staff)"},{"run_index":25,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)"},{"run_index":26,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)"},{"run_index":27,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (deputy chief of staff)"},{"run_index":28,"verdict":3,"source":"human","note":"article handling","answer":"new Senator from Ohio"},{"run_index":29,"verdict":3,"source":"human","note":"answer expanded","answer":"new Senator from Ohio (as deputy chief of staff)"}]},{"eval_id":"019e054b-b654-74aa-b2b0-ad19e229a916","probe":"What is the preferred alternative immunomodulator listed for hospitalized patients requiring HFNC oxygen or NIV?","golden":"IV tocilizumab (Blla)","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"IV tocilizumab (BIIa)"}]},{"eval_id":"019e05b5-b5f0-7a24-b00b-652882db4074","probe":"What plateau pressure does the Panel recommend targeting?","golden":"<30 cm H2O","png_sha":"f2687af1be946044a236b7f11f8cf6f728ef1c4e9e442378d2a6ad846b6a54e4","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O (AIIa)\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":27,"verdict":3,"source":"human","note":"answer expanded","answer":"<30 cm H\u2082O (AIIa)"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"<30 cm H\u2082O"}]},{"eval_id":"019e05e9-158a-7e0b-a377-74df9d26138b","probe":"How many abdominal regions are shown in figure (a)?","golden":"nine","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9\n"},{"run_index":1,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9\n"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9\n"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9\n"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":6,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":7,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":8,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":9,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":10,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":11,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":12,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":13,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":14,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":15,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":16,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":17,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":18,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":19,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":20,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":21,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":22,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":23,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":24,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":25,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":26,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":27,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":28,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"},{"run_index":29,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"9"}]},{"eval_id":"019e05f4-56d1-7193-845a-2889286704f6","probe":"How many abdominal quadrants are shown in figure (b)?","golden":"four","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4\n"},{"run_index":1,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4\n"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4\n"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4\n"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":6,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":7,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":8,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":9,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":10,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":11,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":12,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":13,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":14,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":15,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":16,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":17,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":18,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":19,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":20,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":21,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":22,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":23,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":24,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":25,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":26,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":27,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":28,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":29,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"}]},{"eval_id":"019e0a6f-0c3e-7520-884b-307d309c1b4b","probe":"What percentage of the human body is oxygen?","golden":"65.0%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"65%\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"65%\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"65%  \n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"65%\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":8,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":10,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":12,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":13,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":14,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":19,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":22,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":24,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":26,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"65%"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"65.0"}]},{"eval_id":"019e0a70-8117-7662-8777-c2511bc6f2ee","probe":"What percentage of the human body is phosphorus?","golden":"1.0%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"}]},{"eval_id":"019e0a77-09dc-7990-a971-9e556b040d8c","probe":"What symbol is used to label the electron in the planetary model?","golden":"e\u2212","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"e\u207b"}]},{"eval_id":"019e0a9d-62f1-726d-9b24-bbeb2b85b199","probe":"According to the caption of Figure 3.1.5, which side of the membrane (left or right) shows the hypertonic solution?","golden":"the right side","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":6,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":7,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":8,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":9,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":10,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":11,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":12,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":13,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":14,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":15,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":16,"verdict":3,"source":"human","note":"answer expanded","answer":"right side (of left beaker)"},{"run_index":17,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":18,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":19,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":20,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":21,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":22,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":23,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":24,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":25,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":26,"verdict":3,"source":"precedent","note":"article handling","answer":"right"},{"run_index":27,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":28,"verdict":3,"source":"precedent","note":"article handling","answer":"right side"},{"run_index":29,"verdict":3,"source":"precedent","note":"article handling","answer":"right"}]},{"eval_id":"019e0a9e-aa0f-7a55-89e3-a0cd7f73e21f","probe":"What chemical formula is shown next to each red blood cell in the bottom row of Figure 3.1.6?","golden":"H2O","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O  \n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"H\u2082O"}]},{"eval_id":"019e0ad4-4005-7307-aae9-78e3049f1a65","probe":"What are the three lines that pluripotent embryonic stem cells differentiate into?","golden":"Endoderm, Mesoderm, and Ectoderm","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line\n\n"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line\n\n"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line\n"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line\n"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":6,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":7,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":8,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":9,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":10,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":11,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":12,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":13,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":14,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":15,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":16,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":17,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":18,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":19,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":20,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":21,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":22,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":23,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":24,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":25,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":26,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":27,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":28,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":29,"verdict":3,"source":"precedent","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"}]},{"eval_id":"019e0ed1-c40b-7515-aa9e-86ffff7a7b0a","probe":"In figure (a), labeled \"Loosely held,\" what object is being held?","golden":"a pencil","png_sha":"294a4958d5ff0d4328b9ea9e75f13bb4f7ef1d09ee59316db09945f970fa281f","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":6,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":7,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":8,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":9,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":10,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":11,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":12,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":13,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":14,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":15,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":16,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":17,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":18,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":19,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":20,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":21,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":22,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":23,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":24,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":25,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":26,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":27,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":28,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"},{"run_index":29,"verdict":3,"source":"precedent","note":"article handling","answer":"pencil"}]},{"eval_id":"019e0ed2-1e72-7fe1-94ee-e4dcffb88ace","probe":"In figure (a), what body part is gripping the pencil?","golden":"a hand","png_sha":"294a4958d5ff0d4328b9ea9e75f13bb4f7ef1d09ee59316db09945f970fa281f","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"hand\n"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"hand\n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"hand\n"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"the hand\n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"hand\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":6,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":7,"verdict":3,"source":"human","note":"answer expanded","answer":"hand (fist)"},{"run_index":8,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":9,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":10,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":11,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":12,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":13,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":14,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":15,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":16,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":17,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":18,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":19,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":20,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":21,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":22,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":23,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":24,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":25,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":26,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":27,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":28,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"},{"run_index":29,"verdict":3,"source":"precedent","note":"article handling","answer":"hand"}]},{"eval_id":"019e0ede-f3cd-7412-8c25-2e079510e6e7","probe":"What is the unit shown on the y-axis label?","golden":"mV (millivolts)","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":6,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":7,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":11,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":13,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":22,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"mV"}]},{"eval_id":"019de200-d4b1-72c3-a2c1-2ee5369782dd","probe":"What is the title of Section 31?","golden":"Broker's Commissions","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Broker\u2019s Commissions"}]},{"eval_id":"019de200-d4ba-7ebb-acf4-de78451b07c1","probe":"How many miles is mentioned for relocation of the Executive's principal place of employment?","golden":"25 miles","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"25\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"25\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"25\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25 miles"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"25"}]},{"eval_id":"019de200-d4bd-7e20-a10a-47c622032b52","probe":"What is the item number for the women's Pleated Dress Pants?","golden":"#596","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":6,"verdict":3,"source":"human","note":"answer compressed","answer":"596"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":8,"verdict":3,"source":"human","note":"answer compressed","answer":"596"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"}]},{"eval_id":"019de200-d4c1-76bf-b140-f4b73e70f7ed","probe":"What is the maximum sound level (in dBA) allowed for vacuum cleaners?","golden":"70dBA","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<70 dBA\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"less than 70\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70 dBA\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"less than 70\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70 dBA"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"less than 70"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70 dBA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70 dBA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70 dBA"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"less than 70"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70 dBA"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"less than 70"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"less than 70"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70 dBA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70 dBA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70 dBA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"<70"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70dBA"},{"run_index":24,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"less than 70"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70 dBA"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"less than 70"},{"run_index":27,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"less than 70"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70 dBA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"less than 70 dBA"}]},{"eval_id":"019de200-d4c5-7b98-9a5a-c76d5fb5ae1e","probe":"What is the title of section 5.2?","golden":"Operating Expenses; Consumable Expenses and Base Building Expenses","png_sha":"3343506981bd41f08b63b8df40f8ba763e2bc1566a850d0903f24b1c5782cf77","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses."},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses"}]},{"eval_id":"019de200-d4cb-70dc-a225-ac7807b5a70c","probe":"What is the title of Article 33?","golden":"Costs and Attorneys' Fees","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"}]},{"eval_id":"019de200-d4d6-77e1-9296-5f9e11cf7728","probe":"What does item (c) say?","golden":"Intentionally deleted.","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted).\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)\n\n"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted).\n"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted).\n"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted).\n"},{"run_index":5,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":8,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted)."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":10,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted)."},{"run_index":11,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted)."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":17,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted)."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":21,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted)."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":23,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted)."},{"run_index":24,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted)."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(Intentionally deleted.)"},{"run_index":29,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"(Intentionally deleted)."}]},{"eval_id":"019de200-d4e6-7499-90b0-274586c057d5","probe":"What are the standard business hours listed for Summit's remedial maintenance?","golden":"9:00 am to 5:00 pm, Monday - Friday","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer expanded","answer":"9am-5pm Mon-Fri (holidays excl.)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday (holidays excluded)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday (holidays excluded)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday (Summit holidays excluded)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday (holidays excluded)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday (Summit holidays excluded)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday (Summit holidays excluded)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday (Summit holidays excluded)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (Summit holidays excluded)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)"},{"run_index":19,"verdict":3,"source":"human","note":"answer compressed","answer":"9am-5pm Mon-Fri (excl. holidays)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday (holidays excluded)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday (holidays excluded)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday (holidays excluded)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday (Summit holidays excluded)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (Summit holidays excluded)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday-Friday (holidays excluded)"}]},{"eval_id":"019de200-d4f1-7b08-800d-39648227b1fc","probe":"How many days advance notice must Tenant give for an Acceleration Notice?","golden":"120 days","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"120"}]},{"eval_id":"019de200-d4f7-7940-b10a-9822b81b3272","probe":"What is the Lobby Renovations Allowance?","golden":"$500,000.00","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00 (the \u201cLobby Renovations Allowance\u201d)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00 (\u201cLobby Renovations Allowance\u201d)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":8,"verdict":3,"source":"human","note":"answer expanded","answer":"$500,000 (the \u201cLobby Renovations Allowance\u201d)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00 (Five Hundred Thousand and No/100 Dollars)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00 (\u201cLobby Renovations Allowance\u201d)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00 (the \u201cLobby Renovations Allowance\u201d)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00 (Five Hundred Thousand and No/100 Dollars)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00 (Five Hundred Thousand and No/100 Dollars)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00 (Five Hundred Thousand and No/100 Dollars)"},{"run_index":25,"verdict":3,"source":"human","note":"answer expanded","answer":"$500,000 (the \u201cLobby Renovations Allowance\u201d)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00 (the \u201cLobby Renovations Allowance\u201d)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"}]},{"eval_id":"019de200-d4f8-7a38-8a19-517016d4b55b","probe":"What is the Initial Build-Out Allowance per RSF?","golden":"$48.00","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF (Initial Premises excl. 2nd floor)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF"},{"run_index":6,"verdict":3,"source":"human","note":"answer expanded","answer":"$48/RSF"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00/RSF"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00 per RSF"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00"}]},{"eval_id":"019de200-d507-733d-8d8c-87040ba6130c","probe":"How many days does Landlord have to give Tenant a termination notice after submission of the statement?","golden":"30 days","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"30\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"30\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"30\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"30\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"30\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"** 30\n\n**"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"30"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"}]},{"eval_id":"019de200-d50e-7050-b563-d96d07356800","probe":"How many times per day must the exterior of the building be inspected and maintained?","golden":"four times per day","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4\n"},{"run_index":1,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4\n"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4 times per day\n"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":7,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":8,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4 times"},{"run_index":9,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":10,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":12,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":13,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"four times"},{"run_index":15,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":16,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":17,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":18,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":19,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":20,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4 times per day"},{"run_index":21,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":22,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":23,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":24,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":25,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":26,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":27,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"},{"run_index":28,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4 times per day"},{"run_index":29,"verdict":3,"source":"precedent","note":"numeral/spelled-out","answer":"4"}]},{"eval_id":"019de200-d518-778a-9421-02c7d2e3a05a","probe":"What is the section number for 'Time is of the Essence'?","golden":"Section 1.4","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.4"}]},{"eval_id":"019dfaef-4f26-7d15-9caf-4928cafc4f5e","probe":"What is the exhibit number shown at the top right of this page?","golden":"Exhibit 23.1","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"23.1"}]},{"eval_id":"019dfffd-a1d4-7a49-94b8-3ef9aa5497d4","probe":"What are the two highest courts shown under the Judicial branch?","golden":"The Supreme Court of Texas and The Court of Criminal Appeals","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals\n"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*\n\n"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*\n"},{"run_index":5,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":6,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":7,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":8,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":9,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":10,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":11,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":13,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":14,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":15,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":16,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":17,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":18,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":19,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":20,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":21,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":22,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":23,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":24,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":25,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":26,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":27,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":28,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"},{"run_index":29,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The Supreme Court of Texas* and The Court of Criminal Appeals*"}]},{"eval_id":"019e0009-af38-766a-9ac7-cb0908ad2999","probe":"What percent of the assets of the Colleges and Universities does the University of Texas System constitute?","golden":"72.9 percent","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%\n"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":7,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"72.9"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":12,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":13,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":14,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":15,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":16,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":20,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":22,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":23,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":24,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":25,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":27,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":28,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"72.9%"}]},{"eval_id":"019e000a-7052-7138-b0db-733f874d02cd","probe":"What percent of the expenditures for the State Highway Fund does the Texas Department of Transportation constitute?","golden":"99.9 percent","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"99.9%\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"99.9%\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"99.9%\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"99.9%\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"99.9%\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"** 99.9%\n\n**"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":10,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":11,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":22,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":25,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"},{"run_index":29,"verdict":3,"source":"precedent","note":"glyph variant","answer":"99.9%"}]},{"eval_id":"019e001f-f83d-78ad-bad5-21b87bdb9833","probe":"According to the auditor's report, the Pension Trust Funds represent what percentages of the assets, financial position, and revenues respectively?","golden":"92%, 100%, and 72%","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%\n"},{"run_index":1,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%\n"},{"run_index":2,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%\n"},{"run_index":3,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%\n"},{"run_index":4,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":8,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":11,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%"},{"run_index":12,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":14,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":16,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%"},{"run_index":17,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%"},{"run_index":18,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":20,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%"},{"run_index":21,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":25,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%"},{"run_index":26,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%"},{"run_index":27,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"92%, 100%, 72%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"}]},{"eval_id":"019e003d-d1bc-7fb0-a78b-4b79600f8252","probe":"Who is the Custodian of Funds?","golden":"Brad Lander, Comptroller of the City of New York","png_sha":"89c77daf9c6f881f0116f445cbf736cffc12698b60a93b437699a1a075b00138","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York\n"},{"run_index":4,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":10,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":12,"verdict":3,"source":"precedent","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York"}]},{"eval_id":"019e007d-e19f-7d15-815d-b4e94383d99b","probe":"What are the total expenses for Health and Human Services?","golden":"$75,194 million","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million\n"},{"run_index":2,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (in millions)\n"},{"run_index":3,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (in millions)\n"},{"run_index":4,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)\n"},{"run_index":5,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":6,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":7,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":8,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":9,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":10,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (in millions)"},{"run_index":11,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":12,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":13,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":14,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (in millions)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":16,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (in millions)"},{"run_index":17,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":18,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (in millions)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":21,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (in millions)"},{"run_index":22,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":23,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":24,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$75,194 million"},{"run_index":27,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":28,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (millions)"},{"run_index":29,"verdict":3,"source":"human","note":"magnitude in parenthetical","answer":"$75,194 (in millions)"}]},{"eval_id":"019e00a4-d8d8-7d76-84d9-c255fd95f7cd","probe":"How many minutes is Mrs. Trahan recognized for?","golden":"5 minutes","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019e00a7-39d7-723b-9490-eca9ac160ad7","probe":"What time did the House reconvene after recess?","golden":"1:30 p.m.","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (by Mr. Steube)  \n"},{"run_index":2,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (1330)\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m. \n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (by Mr. STEUBE)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (Mr. STEUBE)"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (1 o'clock and 30 minutes p.m.)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (1 o'clock and 30 minutes p.m.)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (Mr. STEUBE)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (by Mr. STEUBE)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (Mr. Steube)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (by Mr. STEUBE)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (Mr. STEUBE)"},{"run_index":16,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (by Mr. Steube)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (Mr. STEUBE)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (Mr. STEUBE)"},{"run_index":20,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (by Mr. Steube)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (Mr. STEUBE)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (Mr. STEUBE)"},{"run_index":25,"verdict":3,"source":"precedent","note":"answer expanded","answer":"1 o\u2019clock and 30 minutes p.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (by Mr. Steube)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (Mr. STEUBE)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (by Mr. STEUBE)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:30 p.m. (Mr. STEUBE)"}]},{"eval_id":"019e00b5-3554-76cc-805e-ff8228bfefae","probe":"What was the rollcall vote number for the vote on Amendment No. 8?","golden":"Rollcall Vote No. 6 Leg.","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6 (Rollcall Vote No. 6 Leg.)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg.\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6 Leg."},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6 (Rollcall Vote No. 6 Leg.)"},{"run_index":12,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6 Leg."},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6 Leg."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6 Leg."},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 6 Leg."},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6 Leg."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6 (Rollcall Vote No. 6 Leg.)"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6 Leg."},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"6"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6 Leg."},{"run_index":29,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6 Leg."}]},{"eval_id":"019e00b6-0ba2-731c-a9ed-436b1a7ef320","probe":"What was the rollcall vote number for the vote on S. 5?","golden":"Rollcall Vote No. 7 Leg.","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7 Leg.\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7 Leg.\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7 Leg. \n"},{"run_index":5,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7 Leg."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":7,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7 Leg."},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7 Leg."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7 (Rollcall Vote No. 7 Leg.)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":13,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7 Leg."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7 Leg."},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":18,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7 Leg."},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":20,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7 Leg."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7 (Rollcall Vote No. 7 Leg.)"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7 Leg."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7 (Rollcall Vote No. 7 Leg.)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7 (Rollcall Vote No. 7 Leg.)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."},{"run_index":27,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7 Leg."},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"7"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rollcall Vote No. 7 Leg."}]},{"eval_id":"019e00c9-4d63-7e78-a3b2-fd24f554e0db","probe":"What was the largest single contribution amount listed in the Spouse section?","golden":"$25,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":24,"verdict":3,"source":"human","note":"answer compressed","answer":"25000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"}]},{"eval_id":"019e0520-1d4b-7483-9ed6-1c012178bbd9","probe":"How many years has Jess Andrews run Senator Kennedy's communications shop?","golden":"5 years","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 years"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019e0550-c523-7e3c-a7bb-5e58b208e5dc","probe":"In the CATCO trial, what percentage of patients were on conventional oxygen?","golden":"54%","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54% \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":24,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"54"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"}]},{"eval_id":"019e0555-7910-7ed7-a44b-456f65b6a4b0","probe":"Approximately what fraction of patients in the Solidarity trial received corticosteroids?","golden":"two-thirds","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds (approx. 2/3)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds (approx.)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds (approx.)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds\n"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"~2/3\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds (approx. 2/3)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds (approx. 2/3)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds (approx. 2/3)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds (2/3)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds (approx.)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"}]},{"eval_id":"019e05ac-b930-79c4-93f6-be96e504477e","probe":"Within how many months of a recent SARS-CoV-2 infection may substantial immunity be conferred, according to footnote b?","golden":"3-6 months","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"3-6\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"3-6\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"3-6\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":6,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":7,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":8,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":9,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":12,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136"},{"run_index":13,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":15,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":16,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136 months"},{"run_index":17,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":20,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136"},{"run_index":21,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":23,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":24,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":26,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3\u20136"},{"run_index":27,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":28,"verdict":3,"source":"precedent","note":"glyph variant","answer":"3-6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"}]},{"eval_id":"019e05b1-edb1-71fd-a8f1-178c8ce2372a","probe":"How many hours per day of prone ventilation does the Panel recommend?","golden":"12 to 16 hours","png_sha":"f2687af1be946044a236b7f11f8cf6f728ef1c4e9e442378d2a6ad846b6a54e4","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"12 to 16"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"12 to 16"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"12 to 16"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"12 to 16"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"12 to 16"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"12 to 16"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"12 to 16"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"12 to 16"}]},{"eval_id":"019e05e7-ce2c-772c-8efd-a4776364273c","probe":"What is the figure number for the blood pressure image?","golden":"Figure 1.0","png_sha":"4fb66d797829b4efe7d38ed6d367871d6664885f70ef83a42d3f0dfec31552e6","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":13,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.0"}]},{"eval_id":"019e0a70-2afd-7288-98b1-ce3d3fbfaa95","probe":"What percentage of the human body is calcium?","golden":"1.5%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":6,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%"},{"run_index":14,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":17,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":18,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":19,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":23,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"1.5"}]},{"eval_id":"019e0a71-574c-7f62-97db-97525ad2820e","probe":"What is the figure number for the two models of atomic structure?","golden":"Figure 2.1.2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":7,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":8,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":9,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":10,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":11,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":12,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":15,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":16,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":20,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":21,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":22,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 2.1.2"},{"run_index":24,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":25,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":26,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":27,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":28,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"},{"run_index":29,"verdict":3,"source":"precedent","note":"unit/prefix in probe","answer":"2.1.2"}]},{"eval_id":"019e0a76-b33e-7648-8be4-ced32e601bf5","probe":"What element is shown in the planetary model?","golden":"Helium (He)","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"helium (He)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":6,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"He (Helium)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":8,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"He (helium)"},{"run_index":9,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"He (helium)"},{"run_index":10,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"He (helium)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"helium (He)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":15,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"He (helium)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":18,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"He (helium)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"helium (He)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":21,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"He (Helium)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":23,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"He (helium)"},{"run_index":24,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"He (helium)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"helium (He)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"helium (He)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Helium (He)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"helium (He)"}]},{"eval_id":"019e0a82-da2f-727f-896b-27e752c2b42b","probe":"What are the two types of fatty acids labeled in the phospholipid diagram?","golden":"Saturated fatty acid and unsaturated fatty acid","png_sha":"a2c418cbcdc6704d925ad4ffdd78dee38a58fc1ea68774d0094b65c486a66bf8","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"saturated and unsaturated fatty acids\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid\n\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"saturated and unsaturated fatty acids\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":6,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"saturated fatty acid, unsaturated fatty acid"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"saturated and unsaturated fatty acids"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":12,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"saturated fatty acid, unsaturated fatty acid"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":14,"verdict":3,"source":"precedent","note":"answer compressed","answer":"saturated and unsaturated fatty acids"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"saturated and unsaturated fatty acids"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"saturated and unsaturated fatty acids"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"saturated and unsaturated fatty acids"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":21,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"saturated fatty acid, unsaturated fatty acid"},{"run_index":22,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"saturated fatty acid, unsaturated fatty acid"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"},{"run_index":24,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"saturated fatty acid, unsaturated fatty acid"},{"run_index":25,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"saturated fatty acid, unsaturated fatty acid"},{"run_index":26,"verdict":3,"source":"precedent","note":"answer compressed","answer":"saturated and unsaturated"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"saturated & unsaturated fatty acids"},{"run_index":28,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"saturated fatty acid; unsaturated fatty acid"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"saturated fatty acid and unsaturated fatty acid"}]},{"eval_id":"019e0b18-8c5a-7124-bb30-6bd93445411f","probe":"What does the label point to in the middle diagram?","golden":"Cell division accelerates","png_sha":"c97dbfb9dac36762398856cdab61d5779eae44284b94b744c8e56704bbf954e8","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer expanded","answer":"pink cells (accelerated division)\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer expanded","answer":"accelerated cell division (pink area)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":9,"verdict":3,"source":"human","note":"answer expanded","answer":"pink cells (accelerated division region)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":13,"verdict":3,"source":"human","note":"answer expanded","answer":"** pink cells (accelerated division region)\n\n**"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates**\n\n**"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"}]},{"eval_id":"019e0ec6-5ccb-7a48-a454-ea039c311db0","probe":"In the leftmost (first) stage of figure (a), what two structures are labeled?","golden":"Nucleus and Axon","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":24,"verdict":3,"source":"precedent","note":"list separator/conjunction","answer":"Nucleus, Axon"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"}]},{"eval_id":"019e0eea-1322-709e-b1c1-430100607e7d","probe":"In panel (c), what four products come OUT of cellular respiration?","golden":"ATP, Heat, CO\u2082, H\u2082O","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** ATP, Heat, CO\u2082, H\u2082O\n\n**"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":14,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O"},{"run_index":18,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":19,"verdict":3,"source":"precedent","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, heat, CO\u2082, H\u2082O"}]},{"eval_id":"019e0eea-ac39-7b97-941e-8c1e0a744ae3","probe":"In panel (c), what additional input enters the mitochondria from above (with a downward arrow)?","golden":"O\u2082 (oxygen)","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)\n\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)\n"},{"run_index":5,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)"},{"run_index":8,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":9,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":10,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)"},{"run_index":12,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)"},{"run_index":15,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)"},{"run_index":17,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":18,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":19,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)"},{"run_index":23,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":24,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O\u2082 (oxygen)"},{"run_index":27,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":28,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"},{"run_index":29,"verdict":3,"source":"precedent","note":"answer compressed","answer":"O\u2082"}]},{"eval_id":"019e0ef0-10bf-71af-9ca6-cd2d668f1d1c","probe":"In Figure 17.5.2, what does step 6 describe the effects of?","golden":"calcitonin on bone","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"calcitonin (on bone) \n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"calcitonin (on bone)\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"calcitonin (on bone)\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"calcitonin (on bone)\n"},{"run_index":5,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":6,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":7,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":8,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":9,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":10,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":11,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":12,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":13,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":14,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":16,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":18,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":19,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":20,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":21,"verdict":3,"source":"precedent","note":"answer compressed","answer":"calcitonin"},{"run_index":22,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":23,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":24,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":25,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":26,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":29,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"calcitonin (on bone)"}]},{"eval_id":"019de200-d48b-7a0c-9e79-d846c27a96b5","probe":"What page does Article XI Security Deposit start on?","golden":"50","png_sha":"625ba89847b64383ae07efde4a0b7374c88fd2b6dcff552df6812dad32d03160","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"}]},{"eval_id":"019de200-d48c-70ff-b28a-a9c240e3486b","probe":"Who is the landlord named on this office lease?","golden":"Lanham Office 2015 LLC","png_sha":"625ba89847b64383ae07efde4a0b7374c88fd2b6dcff552df6812dad32d03160","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"}]},{"eval_id":"019de200-d48d-703c-b522-b34424519003","probe":"What is Exhibit L?","golden":"Competitor List","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"}]},{"eval_id":"019de200-d48e-767a-b928-9b2d12086653","probe":"What is Exhibit H?","golden":"Roof Access Agreement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"}]},{"eval_id":"019de200-d48f-7596-abf5-cacd23054c4d","probe":"What is Exhibit J?","golden":"Parking Easement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"}]},{"eval_id":"019de200-d490-71ff-a39d-ee962a11796e","probe":"What is Exhibit D?","golden":"Certificate Affirming the Must Take Commencement Date","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"}]},{"eval_id":"019de200-d491-71d6-875d-4fa564623978","probe":"What is Exhibit B?","golden":"Work Agreement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"}]},{"eval_id":"019de200-d492-726b-87fc-5718790d5ebd","probe":"What is Exhibit E?","golden":"Measurement Schedule","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"}]},{"eval_id":"019de200-d493-74c3-af46-0469929cc88d","probe":"What is the Tenant Notice Address?","golden":"8201 Corporate Drive, Suite 900, Landover, MD 20785","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attn: Chief Financial Officer (until full ops at Premises, then Premises), copy to General Counsel\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full ops at Premises); thereafter the Premises, Attn: Chief Financial Officer (copy: General Counsel)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises; thereafter, the Premises, Attn: CFO; copy to General Counsel)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attn: Chief Financial Officer (until full ops at Premises, then Premises), copy to General Counsel\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises, then Premises, Attn: CFO; copy to General Counsel)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises; thereafter the Premises, Attn: CFO; copy to General Counsel)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full ops at Premises; thereafter the Premises, Attn: CFO; copy to General Counsel)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full ops at Premises); thereafter the Premises, Attn: Chief Financial Officer; copy to General Counsel"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises; thereafter the Premises, Attn: CFO; copy to General Counsel)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full ops at Premises; thereafter the Premises, Attn: CFO; copy to General Counsel)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises; thereafter the Premises); copy to General Counsel"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises; thereafter the Premises, same attention; copy to General Counsel)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises); thereafter, the Premises, Attention: Chief Financial Officer (copy to General Counsel)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises; thereafter the Premises, Attn: CFO; copy to General Counsel)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises; thereafter the Premises, Attn: CFO; copy to General Counsel)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises; thereafter the Premises, Attn: CFO; copy to General Counsel)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations, then Premises); copy to General Counsel"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises; thereafter the Premises); copy to General Counsel"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full ops at Premises; thereafter the Premises; copy to General Counsel)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations, then the Premises)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises; thereafter the Premises, Attn: CFO; copy to General Counsel)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises); thereafter, the Premises, Attention: Chief Financial Officer (copy to General Counsel)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full ops at Premises; thereafter the Premises, Attn: CFO; copy to General Counsel)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full ops at Premises; thereafter the Premises); copy to General Counsel"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises), thereafter the Premises, Attention: Chief Financial Officer; copy to General Counsel"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full ops at Premises; thereafter the Premises, Attn: CFO; copy to General Counsel)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full ops at Premises; thereafter the Premises), with copy to General Counsel"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full ops at Premises), thereafter the Premises (Attn: CFO); copy to General Counsel"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations, then the Premises); copy to General Counsel"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer (until full operations at Premises; thereafter, the Premises); copy to General Counsel"}]},{"eval_id":"019de200-d494-73d8-930e-be33d26373fa","probe":"What section is referenced for the definition of 'Tax Benefits'?","golden":"Section 5.6","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"}]},{"eval_id":"019de200-d495-7bf0-9c87-96d57c098e71","probe":"What section is referenced for the definition of 'Threshold Successors'?","golden":"Section 10.1","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"}]},{"eval_id":"019de200-d497-758c-9ad2-fceee7efd1fa","probe":"What section is referenced for the definition of 'Tenant's Plans'?","golden":"Section 9.4(a)","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"}]},{"eval_id":"019de200-d498-741d-b3e0-3374c9b02dfc","probe":"What is the title of section H?","golden":"Tenant Modular Furniture","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"}]},{"eval_id":"019de200-d49a-7b22-8b95-3fe120b21efc","probe":"What is the section number for the CARPET section?","golden":"09680","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"}]},{"eval_id":"019de200-d49b-76ae-aecb-69e6ba967a73","probe":"What is the section number for the PAINTING section?","golden":"09900","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"}]},{"eval_id":"019de200-d49c-75ca-963f-0649d0c70719","probe":"What is the section number for ACOUSTICAL CEILING?","golden":"09510","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"}]},{"eval_id":"019de200-d49d-7cee-91a2-4ed07626e90a","probe":"What is the name of the company shown in the schedule heading on this page?","golden":"Acadia Realty Trust","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"}]},{"eval_id":"019de200-d49e-7120-8c57-be2e37f1a894","probe":"What is the page number shown at the bottom of the upper section of this page?","golden":"166","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"}]},{"eval_id":"019de200-d49f-72ce-9b9d-97ba16d5640c","probe":"What is the depreciation period (useful life in years) listed in the rightmost column for every property on this page?","golden":"40 years","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years (all properties)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years (all properties)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years (all properties)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years (all properties)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years (all properties)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years (all properties)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years (all properties)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years (every property)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years (all properties)"}]},{"eval_id":"019de200-d4a1-7f82-aa55-38eac3b9b487","probe":"What is the total deferred tax assets for 2017 (in thousands)?","golden":"145,657","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657**  \n**"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145657"}]},{"eval_id":"019de200-d4a2-7a39-91ad-766fdf7c2010","probe":"What is the page number shown at the bottom center of the page?","golden":"F-29","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"}]},{"eval_id":"019de200-d4a3-7518-9715-cc1bb9edb084","probe":"What is the deferred revenue amount for 2016 (in thousands)?","golden":"1,666","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"}]},{"eval_id":"019de200-d4a5-753e-87a5-2c51cb711be4","probe":"What is the Research and development credits amount for 2017 (in thousands)?","golden":"12,548","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12548"}]},{"eval_id":"019de200-d4a6-72d4-b715-3cd7f42e4f66","probe":"What is the State income tax, net of federal benefit percentage for 2016?","golden":"5.9%","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"}]},{"eval_id":"019de200-d4a7-74af-afa8-d3ad189499cc","probe":"What is the deposit amount mentioned in this document?","golden":"$500,000.00","png_sha":"5a5e3841491b2b356eb9b963e45419183ebf6ffae298e69a6f9dd5488bc23e1c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"}]},{"eval_id":"019de200-d4a8-7bdc-bc00-d50a60d60dcc","probe":"What is the title of section 16?","golden":"Mutual Waiver of Subrogation Rights","png_sha":"674a83793665d045c76513a816f7fc9099c52baccd94af7ee817a5f89cdc81d5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights."}]},{"eval_id":"019de200-d4a9-7107-917d-4d1e160c26b3","probe":"What is the anticipated commencement date?","golden":"March 1, 2016","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"}]},{"eval_id":"019de200-d4aa-7225-85f5-76e6b1382af9","probe":"What is the premises address?","golden":"2665 North First Street, Suite 300, San Jose, California 95134","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"}]},{"eval_id":"019de200-d4ab-727c-ae0c-07bdc5f94836","probe":"What is the tenant's trade name?","golden":"8x8, Inc.","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."}]},{"eval_id":"019de200-d4ac-742d-b65a-74bd92f2893d","probe":"What is the name of the broker listed in Section 31?","golden":"Cresa Global, Inc.","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."}]},{"eval_id":"019de200-d4ad-71b2-aae9-616c2d5fdb91","probe":"What is the title of Section 33?","golden":"Holding Over","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"}]},{"eval_id":"019de200-d4ae-7bb5-8e56-dfba0d289a6a","probe":"What is the title of Section 38?","golden":"Miscellaneous","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"}]},{"eval_id":"019de200-d4af-7ae9-9bf2-f9ad2d8f5ea5","probe":"What is the title of Section 32?","golden":"Estoppel Certificate","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"}]},{"eval_id":"019de200-d4b0-7068-9693-c265751b0823","probe":"What is the title of Section 34?","golden":"Assignment and Subletting","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"}]},{"eval_id":"019de200-d4b2-7946-80ee-a29424252d23","probe":"What is the title of section 14.3?","golden":"Transfer Premium","png_sha":"cde4659cf5512e2c7b127af66eb4bab815dcc533bb04fce540d6d56b21cbb6cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"}]},{"eval_id":"019de200-d4b3-7330-8b3a-3010528a30fa","probe":"What is the title of section 14.5?","golden":"Effect of Transfer","png_sha":"cde4659cf5512e2c7b127af66eb4bab815dcc533bb04fce540d6d56b21cbb6cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"}]},{"eval_id":"019de200-d4b4-702e-932f-bb5b6dbb2b20","probe":"What is the title of Article XXIX?","golden":"Expansion Rights","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"}]},{"eval_id":"019de200-d4b5-709e-9897-f8440e2a964f","probe":"What is the title of Article XXX?","golden":"METROPLEX II ASSUMPTION","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION"}]},{"eval_id":"019de200-d4b6-73e9-aa56-a2eb7119541a","probe":"What is the title of Section 29.1?","golden":"Right of First Refusal","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** Right of First Refusal\n\n**"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"}]},{"eval_id":"019de200-d4b7-7604-b550-db1d11ebef12","probe":"What is the title of Section 28.2?","golden":"Additional Amenities","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities."}]},{"eval_id":"019de200-d4b8-7164-91b2-3ec03d9f397f","probe":"What is the title of section 12?","golden":"Severance Payments","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"}]},{"eval_id":"019de200-d4b9-723f-8a38-4f373e93bffa","probe":"What is the title of section 13?","golden":"Certain Covenants of the Executive","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive."}]},{"eval_id":"019de200-d4bb-7ca6-ada6-5158e0ca9947","probe":"What is the item number for the Foreperson/Day Porter Executive dress shirt?","golden":"#828","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"}]},{"eval_id":"019de200-d4bc-76fc-9589-06797f38e895","probe":"What is the title of section E?","golden":"UNIFORMS","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"E. UNIFORMS"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"}]},{"eval_id":"019de200-d4be-7e4d-b5ce-bf5d0d9e3745","probe":"What is the title of section J?","golden":"LIGHTING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"}]},{"eval_id":"019de200-d4bf-7a42-91f9-d00fe759f635","probe":"What is the title of section H?","golden":"SECURITY AND INCIDENT REPORTING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"}]},{"eval_id":"019de200-d4c0-7843-8047-cc09e991e12b","probe":"What is the title of section K?","golden":"GREEN CLEANING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"}]},{"eval_id":"019de200-d4c2-7ad3-88a8-ed0b24b345b7","probe":"What is the item number for the men's Foreperson/Day Porter Pleated dress pants?","golden":"#865","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"}]},{"eval_id":"019de200-d4c3-7771-b087-cb7f248214a4","probe":"What is the item number listed for the women's Long Sleeve Dress Blouse?","golden":"#528","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"}]},{"eval_id":"019de200-d4c4-736b-b432-833199724c46","probe":"What is the title of section 24.0?","golden":"HOLDOVER","png_sha":"214b816ecbf747322726d54a0cb92edd6d184be6a6e04656e532d637c65eda11","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"}]},{"eval_id":"019de200-d4c6-7729-866a-8ac3402457fb","probe":"What is the title of Article XIV?","golden":"Assignment and Subletting","png_sha":"d8fa233fb12db1beef1e4088d39215700d5884c2d4cb968b6985c6febde8a2ca","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"}]},{"eval_id":"019de200-d4c7-7305-82b7-76d4d75e7f9d","probe":"What is the title of Article XIII?","golden":"Condemnation","png_sha":"d8fa233fb12db1beef1e4088d39215700d5884c2d4cb968b6985c6febde8a2ca","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"}]},{"eval_id":"019de200-d4c8-787c-9ed4-e33640efb435","probe":"What is the title of Article 28?","golden":"Confidentiality","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality"}]},{"eval_id":"019de200-d4c9-7b7f-9e32-c47d4f1c0b0e","probe":"What is the title of Exhibit D?","golden":"Form of Deed","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"}]},{"eval_id":"019de200-d4ca-7805-9cc9-6e26cd367bbc","probe":"What is the title of Article 25?","golden":"Waiver of Jury Trial","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"}]},{"eval_id":"019de200-d4cc-7013-9323-c4a463e49255","probe":"What is the Lessor's telephone number listed in the notices section?","golden":"(81) 8358.7978","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"}]},{"eval_id":"019de200-d4cd-7c1a-a4b1-fd5dc2875413","probe":"What is the title of section 24.4?","golden":"Captions","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"}]},{"eval_id":"019de200-d4ce-73b9-b787-b0f7568e7018","probe":"What is the Lessee's telephone number listed in the notices section?","golden":"(81) 8158.8800","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800"}]},{"eval_id":"019de200-d4cf-7e95-8f4b-cca6ed5396ce","probe":"What is the title of section 24.5?","golden":"Severability","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability."}]},{"eval_id":"019de200-d4d0-7008-bd98-2d410f1fb7fa","probe":"What is the name of the person to contact for the Lessor in the notices section?","golden":"Mr. Juan Carlos Gonzalez Quezada","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"}]},{"eval_id":"019de200-d4d1-7e39-92cb-dc82b006e040","probe":"What is the title of section 24.1?","golden":"Brokers","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"}]},{"eval_id":"019de200-d4d2-7ff3-ae3f-b7ce26ebedc4","probe":"What is the title of section 22.3?","golden":"Labor","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor.\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"}]},{"eval_id":"019de200-d4d4-7185-bf69-9197f90e27ce","probe":"What is the title of Section II?","golden":"TENANT'S WORK","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"}]},{"eval_id":"019de200-d4d5-7ac3-8e4e-c758cbae290a","probe":"What is the per square foot dollar amount mentioned for the Allowance?","golden":"$40.00","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00"}]},{"eval_id":"019de200-d4d7-71ee-b89a-13f57933c5ed","probe":"What is the company name shown in the headers of the financial statements?","golden":"Acadia Realty Trust and Subsidiaries","png_sha":"d99abf4bae64753a77c680d1e83acdbdc08eb377e9da9bc0a4af8337f67971e2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust and Subsidiaries"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"}]},{"eval_id":"019de200-d4d8-73df-b318-56c93e913a1d","probe":"What is the rent payable for December 2016 in the Metroplex Rent table?","golden":"137,399","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137399\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137399\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137399"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137399"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"}]},{"eval_id":"019de200-d4d9-7080-91a1-8e4024ae5b27","probe":"What is the title of Exhibit M?","golden":"Metroplex Rent","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"}]},{"eval_id":"019de200-d4da-740b-af0a-30cdbbdc3a00","probe":"What is the rent payable for July 2018?","golden":"145,763","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"}]},{"eval_id":"019de200-d4db-76f8-b9cf-eb901aaef607","probe":"What is the title of Exhibit N?","golden":"Exclusions From Operating Expenses","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"}]},{"eval_id":"019de200-d4dc-76d9-b19c-2bb2f2c2d455","probe":"What is the rent payable for March 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4dd-7a8e-97e8-6cbb97c9f288","probe":"What is the rent payable for January 2018?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4de-7510-a1bb-a2200cf532b1","probe":"What is the rent payable for May 2018?","golden":"145,763","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145763"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"}]},{"eval_id":"019de200-d4df-72db-b8e2-5470717b76c7","probe":"What is the rent payable for September 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4e0-7497-8998-04b404a57589","probe":"What is listed as item (i) under Excluded Expenses in Exhibit N?","golden":"Real Estate Taxes","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes;"}]},{"eval_id":"019de200-d4e1-704d-bad7-731b3da45bdf","probe":"What is the rent payable for November 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141524"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4e2-7aab-ae79-29c74e645fca","probe":"What is the title of Exhibit C?","golden":"Technology Exhibit","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"}]},{"eval_id":"019de200-d4e3-7937-8135-40c4b4f0cb8e","probe":"What is the markup percentage on outgoing mail?","golden":"10%","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"}]},{"eval_id":"019de200-d4e4-7765-86d5-d5fb371119ed","probe":"What is the title of Exhibit B?","golden":"Summit Billing Information","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"}]},{"eval_id":"019de200-d4e5-7bb2-9e8d-5d17eac142de","probe":"What is the reconnection fee per hour mentioned in Exhibit C?","golden":"$100","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"}]},{"eval_id":"019de200-d4e7-7aba-997b-697fce37c98b","probe":"Who signed as Chief Executive Officer of 1847 Holdings LLC?","golden":"Ellery W. Roberts","png_sha":"17421f00db7e68e09f420ba5abd403a8bc79b47f8f380327515bff5297f38fed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"}]},{"eval_id":"019de200-d4e8-7f62-96ae-519b14f37f5f","probe":"On what day of December 2024 did the Guarantors execute this Guaranty?","golden":"13th","png_sha":"17421f00db7e68e09f420ba5abd403a8bc79b47f8f380327515bff5297f38fed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"}]},{"eval_id":"019de200-d4e9-71c2-9557-1e2c70c1e1fb","probe":"What is the Per RSF Base Rent for the Initial Term?","golden":"$20.50","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50 (Twenty and 50/100 Dollars)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50 (Twenty and 50/100 Dollars)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50 (Twenty and 50/100 Dollars)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$20.50 (Twenty and 50/100 Dollars)"}]},{"eval_id":"019de200-d4eb-7ccd-933d-0af15a613cf0","probe":"What is the Alteration Threshold dollar amount?","golden":"$200,000.00","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"}]},{"eval_id":"019de200-d4ec-7fff-aceb-46c812561273","probe":"Which floors of the Building are designated as the Must Take Expansion Premises?","golden":"Floors 5, 6 and 7","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7"}]},{"eval_id":"019de200-d4ed-7a5a-bca1-903c35b0c671","probe":"What is the speed limit mentioned in rule 4 of the parking rules?","golden":"5 miles per hour","png_sha":"4a35d25bb27a032bf2661265ea4187cfc0129b1d6aa4a12ae16fc6380aea8e4c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"}]},{"eval_id":"019de200-d4ee-76cd-96ee-560ea13db477","probe":"What are the parking hours listed in rule 1?","golden":"7:30 a.m. to 6:30 p.m., Monday through Friday","png_sha":"4a35d25bb27a032bf2661265ea4187cfc0129b1d6aa4a12ae16fc6380aea8e4c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"}]},{"eval_id":"019de200-d4f0-7baf-9b58-1e08027b6f0d","probe":"How many RSF is the 2nd Floor Premises calculated as for Base Rent purposes?","golden":"12,000 RSF","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12000 RSF"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"}]},{"eval_id":"019de200-d4f2-7a99-af6e-94a36878aec2","probe":"What is the per-RSF dollar amount used to calculate the Must Take Allowance?","golden":"$46.50","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46.50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46.50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"}]},{"eval_id":"019de200-d4f3-7347-815c-24a4e9f82950","probe":"In the example, what is the Must Take Allowance for the 7th floor?","golden":"$1,198,611.65","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"}]},{"eval_id":"019de200-d4f4-7dcb-9449-8179714e49d7","probe":"What is the limit of liability for Landlord's commercial general liability insurance?","golden":"$5,000,000 per occurrence","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not less than $5,000,000 per occurrence"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence"}]},{"eval_id":"019de200-d4f5-78f3-8340-3580046edcc8","probe":"What is the each occurrence limit for Personal Injury Liability?","golden":"$9,000,000","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000 each occurrence"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"}]},{"eval_id":"019de200-d4f6-7741-884c-42611e27bcef","probe":"What is the Insured's participation percentage for Personal Injury Liability?","golden":"0%","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"}]},{"eval_id":"019de200-d4f9-7748-a94b-9e4c68688de5","probe":"What is the construction supervision fee percentage Landlord charges on hard construction costs?","golden":"1%","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1% (one percent)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"}]},{"eval_id":"019de200-d4fa-70fc-b7a8-b9c26c2b14e0","probe":"By what date must Tenant substantially complete the 2nd Floor Build-Out Work?","golden":"April 1, 2018","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"}]},{"eval_id":"019de200-d4fb-7f01-8927-c6d175a34ace","probe":"By what date must Tenant substantially complete the Initial Build-Out Work of the Initial Premises?","golden":"April 1, 2017","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"}]},{"eval_id":"019de200-d4fc-7cca-908f-984e3d8120e7","probe":"What is the umbrella liability each occurrence amount?","golden":"$5,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"}]},{"eval_id":"019de200-d4fd-74c2-abb8-1bb3a38e217c","probe":"What is the medical payments coverage amount?","golden":"$5,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000"}]},{"eval_id":"019de200-d4fe-76cb-bdd6-bb011389179c","probe":"What is the fire damage legal liability coverage amount?","golden":"$50,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"}]},{"eval_id":"019de200-d4ff-7fd5-9027-7197160465a2","probe":"What is the automobile liability combined single limit amount?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d500-7cfe-8ff2-d8bbbb64073a","probe":"What is the bodily injury by accident coverage amount per accident under Workers' Compensation Coverage B?","golden":"$500,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"}]},{"eval_id":"019de200-d501-782d-845b-a4e35e143c20","probe":"What is the combined single limit per occurrence for Coverage A under Commercial General Liability?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d502-7a8b-9ba6-c9892e2eeecc","probe":"What insurance form is the general liability insurance to be written on?","golden":"2001 Insurance Services Office form","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form (or equivalent)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form (or equivalent)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form (or equivalent)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form (or equivalent)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form (or equivalent)"}]},{"eval_id":"019de200-d503-798a-afa1-45a2677f34db","probe":"What is the personal and advertising injury liability (Coverage B) amount?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d504-70ea-9d31-b199175fed3c","probe":"In what geographic area must business interruption insurance match amounts customarily carried by responsible tenants?","golden":"Greater Boston","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"}]},{"eval_id":"019de200-d506-744e-be70-a75cf629bab5","probe":"What is the non-refundable assignment/sublease review fee?","golden":"$1,500","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"}]},{"eval_id":"019de200-d509-782f-8cb5-81249701c47f","probe":"What percentage of the excess must Tenant pay to Landlord as Assignment/Sublease Excess Rent?","golden":"100%","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100% \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"}]},{"eval_id":"019de200-d50a-7a93-8a69-a34202f99ee3","probe":"What is the term used for the portion of Premises eliminated under the Elimination Period?","golden":"Eliminated Space","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\u201cEliminated Space\u201d"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"}]},{"eval_id":"019de200-d50b-714d-a6f0-8fbb3c33bc67","probe":"What is the term defined for the date immediately prior to the effective date of the proposed assignment?","golden":"Earlier Termination Date","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"rm is the \u201cEarlier Termination Date\u201d.\n\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"}]},{"eval_id":"019de200-d50c-743d-ad76-780e2c2fb12d","probe":"What is the term used for the period after the Elimination Period during which the Eliminated Space is restored to the Premises?","golden":"Restoration Period","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"}]},{"eval_id":"019de200-d50d-7c5f-a9f2-1705d2b33bc2","probe":"What is the term defined for the consideration payable by the assignee or subtenant?","golden":"Assignment/Sublease Consideration","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"}]},{"eval_id":"019de200-d50f-730f-bba3-567d098ebd36","probe":"By what time each weekday must the stainless steel tops on the 18th Street light boxes be wiped down?","golden":"8:00 AM","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"prior to 8:00 AM"}]},{"eval_id":"019de200-d510-7320-b95d-f545ed219bc5","probe":"How often must window frames and ledges be swept with a soft-bristled brush on the building exterior?","golden":"Monthly","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"}]},{"eval_id":"019de200-d511-7272-9565-2412f58e253c","probe":"How often must service area floors be dust mopped, at minimum?","golden":"Once per week","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week (no less than)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week (no less than)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week (no less than)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week (no less than)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week (no less than)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"no less than once per week"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week (no less than)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week (no less than)"}]},{"eval_id":"019de200-d512-7496-808b-5b1ea05ca3f8","probe":"How often must standpipe fire hose connections on the exterior of the building be cleaned and polished?","golden":"Weekly","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"}]},{"eval_id":"019de200-d513-7149-ae8c-e8a7754d572b","probe":"What is the minimum amount for a partial prepayment of Revolving Loans?","golden":"$100,000","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (or higher integral multiple of $25,000)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000 (higher integral multiples of $25,000)"}]},{"eval_id":"019de200-d514-76a5-be6d-0713d4261c08","probe":"What is the full deadline (both time of day and number of business days) by which a Notice of Borrowing must be delivered before a proposed borrowing?","golden":"1:00 p.m. (Eastern time) two (2) Business Days prior","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of such proposed borrowing"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior"}]},{"eval_id":"019de200-d516-7459-9245-cc659422a55c","probe":"By what time on the Termination Date must the entire outstanding principal of each Revolving Loan be paid?","golden":"12:00 Noon (Eastern time)","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time) \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not later than 12:00 Noon (Eastern time)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not later than 12:00 Noon (Eastern time)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not later than 12:00 Noon (Eastern time)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not later than 12:00 Noon (Eastern time)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not later than 12:00 Noon (Eastern time)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not later than 12:00 Noon (Eastern time)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not later than 12:00 Noon (Eastern time)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"not later than 12:00 Noon (Eastern time)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)"}]},{"eval_id":"019de200-d517-7577-ad4f-c469f0a5f3e3","probe":"What is the higher integral multiple required for partial prepayments of Revolving Loans?","golden":"$25,000","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"}]},{"eval_id":"019de200-d519-76a9-b52e-17fb3cd3da08","probe":"What rate do Revolving Loans accrue interest at, plus the Applicable Margin?","golden":"LIBOR Rate","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"}]},{"eval_id":"019de200-d51a-7cbd-841b-aa945ef2b4a8","probe":"Notices of Borrowing must be delivered before what time (Eastern time)?","golden":"1:00 p.m.","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."}]},{"eval_id":"019de200-d51b-7404-9feb-b6384f640f1a","probe":"How many calendar days prior to lease termination must the parties allow Lessor to enter the property for inspection?","golden":"60","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60 calendar days\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60 calendar days\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60 calendar days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60 calendar days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"}]},{"eval_id":"019de200-d51c-7dd7-ad07-e2fd96baf505","probe":"Who conducted the Phase I Environmental Assessment mentioned in section 11.1?","golden":"GAIM REGIOMONTANA","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"}]},{"eval_id":"019de200-d51d-7bbb-9bed-8ceaca14c398","probe":"What is the telephone number listed for Mr. Juan Carlos Gonzalez Quezada?","golden":"(81) 8358.7978","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978"}]},{"eval_id":"019de200-d51e-7caf-b475-352d47499736","probe":"What is the postal code (C.P.) listed in the address for Mr. Juan Carlos Gonzalez Quezada?","golden":"66220","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"}]},{"eval_id":"019de200-d51f-723d-9741-37784d76009a","probe":"What is the telephone number listed for Mr. David Rodriguez Santos at Torre Sienna?","golden":"(81) 8356.1200","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200"}]},{"eval_id":"019de200-d520-7d78-a11e-ce881c0ff357","probe":"How many calendar days does Lessor have to object to a proposed sublease in writing?","golden":"30","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 calendar days\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 calendar days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 calendar days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"}]},{"eval_id":"019de200-d521-77a9-8367-9a4a834e7041","probe":"What is the apartment/interior number (Int.) listed in the address for Torre Sienna?","golden":"1403","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403"}]},{"eval_id":"019de200-d522-7ac9-8bba-7b83fb15043b","probe":"What exhibit is the 'Maintenance Carnet' attached as?","golden":"Exhibit \"J\"","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""}]},{"eval_id":"019de200-d524-75fd-bff6-f429befeae8a","probe":"How many calendar days does Lessee have to dispute damages or Alterations indicated in Lessor's notice?","golden":"15","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15 calendar days\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15 calendar days\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15 calendar days\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15 calendar days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15 calendar days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15 calendar days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15 calendar days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15 calendar days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15 calendar days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15 calendar days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15 calendar days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15 calendar days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"}]},{"eval_id":"019de22d-8775-7482-9f31-5e7710938d70","probe":"What is the original principal amount of the 3.50% Series A Convertible Senior Notes due February 1, 2018?","golden":"$70.3 million","png_sha":"9999d442e3243c2ea48a7de6c4c9b162568b4e59e41492087837bdb419a11d2c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"}]},{"eval_id":"019de778-2487-7ceb-942f-bbc9cce683b5","probe":"What is the public law number?","golden":"118-109","png_sha":"a0300e50b30b31b24996ac843a50187dca0d8e81f6c026161ae3e07159e9815a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"}]},{"eval_id":"019dfae7-e8c3-7289-a5e3-25d26a497795","probe":"What is the fiscal year end date?","golden":"September 28, 2024","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"}]},{"eval_id":"019dfae8-2c75-7590-9083-4c07bf26944a","probe":"What is the Commission File Number?","golden":"001-36743","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"}]},{"eval_id":"019dfae8-8300-75b0-98f0-558c886fd068","probe":"What is the registrant's telephone number?","golden":"(408) 996-1010","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"}]},{"eval_id":"019dfae8-d37e-73db-bad0-7dbbebba1d87","probe":"What is the IRS Employer Identification Number?","golden":"94-2404110","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"}]},{"eval_id":"019dfae9-3119-7c26-b2ed-73fb2888fdfe","probe":"What is the par value per share of Apple's common stock?","golden":"$0.00001","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"}]},{"eval_id":"019dfae9-c244-75c3-92a8-4f02d64471e6","probe":"What were Americas net sales in 2024 (in millions)?","golden":"$167,045","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$167,045\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167045"}]},{"eval_id":"019dfaea-1b4b-7bef-bf30-f8f1ee1cb9d6","probe":"What were Europe net sales in 2024 (in millions)?","golden":"$101,328","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101328"}]},{"eval_id":"019dfaea-c282-7bca-85d8-a2edb7306504","probe":"What were total net sales in 2024 (in millions)?","golden":"$391,035","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391035"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"}]},{"eval_id":"019dfaeb-1b0e-7077-a093-a8a138a79e25","probe":"What were Greater China net sales in 2022 (in millions)?","golden":"$74,200","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74200"}]},{"eval_id":"019dfaec-3d80-7c7c-95b7-6a34a086d48b","probe":"What is the date the report was signed?","golden":"November 1, 2024","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"}]},{"eval_id":"019dfaec-8345-7eea-8840-6867945a7a06","probe":"Who is the Director and Chair of the Board?","golden":"Arthur D. Levinson","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ARTHUR D. LEVINSON"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ARTHUR D. LEVINSON"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson (ARTHUR D. LEVINSON)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ARTHUR D. LEVINSON"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"}]},{"eval_id":"019dfaec-e961-7051-a4ce-b66996997cb2","probe":"Who is the Senior Director of Corporate Accounting?","golden":"Chris Kondo","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"}]},{"eval_id":"019dfaed-c27e-7590-9034-1cc2a5319b55","probe":"Who is the accounting firm that signed this consent?","golden":"Ernst & Young LLP","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"}]},{"eval_id":"019dfaee-6467-74cc-8101-5271bea3e394","probe":"What is the Form S-8 number for the Apple Inc. Employee Stock Purchase Plan?","golden":"333-203698","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"}]},{"eval_id":"019dfaf0-11d2-70d1-be50-371940478750","probe":"Where is Braeburn Capital, Inc. incorporated?","golden":"Nevada, U.S.","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."}]},{"eval_id":"019dfaf0-52d8-7941-b336-19bfbe7f8bc1","probe":"Where is Apple Asia Limited incorporated?","golden":"Hong Kong","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"}]},{"eval_id":"019dfaf1-05a1-718d-818a-e45ba4945ba1","probe":"Where is Apple Operations Mexico, S.A. de C.V. incorporated?","golden":"Mexico","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"}]},{"eval_id":"019dfaf2-2642-7eae-b1fb-1620be9706bc","probe":"Starting on what date does this policy apply to Incentive-Based Compensation that is Received?","golden":"October 2, 2023","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"}]},{"eval_id":"019dfaf3-1977-7337-8a56-6b3d55edd900","probe":"What Nasdaq listing rule was adopted to implement Rule 10D-1 under the Exchange Act?","golden":"Listing Rule 5608","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"}]},{"eval_id":"019dfaf3-d93a-7e7a-8293-bed401dc3c74","probe":"Under what year's Securities and Exchange Act is 'executive officer' defined for this policy?","golden":"1934","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"}]},{"eval_id":"019dfaf4-6d06-7bb4-9da0-5703eced16ad","probe":"What company's logo appears at the top of this policy?","golden":"Apple","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple Inc. (Apple logo)  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple (logo)  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple (Inc.)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple (Apple Inc.)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple (Apple Inc.)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple (Inc.)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple (Inc.)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"}]},{"eval_id":"019dfaf5-67bd-727d-92f0-43a3108e55cf","probe":"What is the commission file number?","golden":"001-37580","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"}]},{"eval_id":"019dfaf5-e414-73d4-a5bb-864069d83389","probe":"What is the IRS Employer Identification Number?","golden":"61-1767919","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"}]},{"eval_id":"019dfaf6-3c67-7437-b33f-106a71df96cc","probe":"What is the registrant's telephone number?","golden":"(650) 253-0000","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"}]},{"eval_id":"019dfaf6-8eaf-75f8-a68a-e019cf9ab6dc","probe":"What is the interest rate of the Senior Notes due 2064?","golden":"4.375%","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"}]},{"eval_id":"019dfaf6-cd98-71f2-9576-0e07833ebd70","probe":"What is the interest rate of the Senior Notes due 2028?","golden":"2.375%","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"}]},{"eval_id":"019dfaf7-7376-72e6-af9f-4f0302bf05aa","probe":"What is the trading symbol for Alphabet's Class C Capital Stock?","golden":"GOOG","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"}]},{"eval_id":"019dfaf7-a3e9-7079-abc1-1170e6a73c4f","probe":"What is the fiscal year end date on this 10-K?","golden":"December 31, 2025","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"}]},{"eval_id":"019dfaf8-f7e3-7fa2-809d-07b2ec3cfaea","probe":"How much remained available for Class A and Class C share repurchases as of March 31, 2025?","golden":"$29.5 billion","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"}]},{"eval_id":"019dfafa-9cb0-7412-8eac-d16591d94510","probe":"What is the quarterly cash dividend declared on April 2025?","golden":"$0.21","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21 per share\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"}]},{"eval_id":"019dfafd-0e8d-7a0f-8f4e-4d3d489b698a","probe":"By what percentage did the Board of Directors increase the quarterly cash dividend in April 2025?","golden":"5%","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5% \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"}]},{"eval_id":"019dfafe-5a0c-7b21-8bfa-72a257476e5a","probe":"What was the total carrying value of senior unsecured notes outstanding as of September 30, 2025?","golden":"$23.6 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"}]},{"eval_id":"019dfaff-051e-7ba2-8350-09ebbfdb115a","probe":"How much remained available for Class A and Class C share repurchases as of September 30, 2025?","golden":"$74.8 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"}]},{"eval_id":"019dfb00-8129-7fae-9c3d-085f17af7163","probe":"How many Class C shares were repurchased in the three months ended September 30, 2025 (in millions)?","golden":"51","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51**\n\n**"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"}]},{"eval_id":"019dfb01-6670-7c43-bf57-578d4e8743df","probe":"How much was the revolving credit facility expiring in April 2030?","golden":"$6.0 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"}]},{"eval_id":"019dfb02-8211-7651-9ec4-8c0ebcf58a3b","probe":"What was the dollar amount of Class A share repurchases for the three months ended September 30, 2025 (in millions)?","golden":"$926","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** 926\n\n**"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"}]},{"eval_id":"019dfb06-2d63-7e40-9cfc-442adddd3a61","probe":"As of what date did the CEO and CFO conclude on the disclosure controls evaluation?","golden":"June 30, 2025","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"}]},{"eval_id":"019dfb06-7255-7580-9ef1-58f24ae75626","probe":"What rule under the Exchange Act was used to evaluate disclosure controls and procedures?","golden":"Rule 13a-15","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"}]},{"eval_id":"019dfb07-58e1-741b-95ae-39f6ad5b9738","probe":"For what quarter ended date is the internal control reporting statement made?","golden":"June 30, 2025","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"}]},{"eval_id":"019dfb08-723b-72c9-8209-4c6b104c74d9","probe":"What form is the Quarterly Report on?","golden":"Form 10-Q","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"}]},{"eval_id":"019dfb09-b2b4-7900-94d0-5ead62b5fa3a","probe":"How much was the initial investment used in the graph comparison?","golden":"$100","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"}]},{"eval_id":"019dfb0a-1542-7607-afff-3824643328be","probe":"On what date does the graph's tracking period end?","golden":"December 31, 2025","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"}]},{"eval_id":"019dfb0a-4250-7161-8e90-fa2502ad8254","probe":"What is the starting date of the graph's tracking period?","golden":"December 31, 2020","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"}]},{"eval_id":"019dfb0a-bbec-7b6d-bb26-274ff05f9459","probe":"What is the highest dollar value shown on the y-axis of the graph?","golden":"$400","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"400\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"400\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"400"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"400"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"400"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"400"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"400"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"400"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"}]},{"eval_id":"019dfb0a-e54b-7973-8d05-99144d938deb","probe":"What color is the line representing the S&P 500 in the graph?","golden":"Green","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"}]},{"eval_id":"019dfb0b-0fe9-717a-b315-903647d9114e","probe":"What color is the line representing Alphabet Inc. Class C in the graph?","golden":"Red","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"}]},{"eval_id":"019dfb0b-9664-7b20-bea5-647276953368","probe":"How much is Alphabet acquiring Wiz, Inc. for?","golden":"$32.0 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"}]},{"eval_id":"019dfb0c-07a8-768c-bf46-7d82769ad116","probe":"What is the long-term income taxes payable as of December 31, 2025?","golden":"$9.5 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"}]},{"eval_id":"019dfb0d-123a-74db-8a55-4a162b6b8cfb","probe":"How much is Alphabet acquiring Intersect for in cash?","golden":"$4.8 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"}]},{"eval_id":"019dfb0d-98a6-7573-8987-ba32c57f6b7a","probe":"What is the total amount of purchase commitments and other contractual obligations as of December 31, 2025?","golden":"$149.1 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"}]},{"eval_id":"019dfb14-6817-7cc7-90e2-fce76cd476e7","probe":"How many employees did JPMorganChase have globally as of December 31, 2025?","golden":"318,512","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318512"}]},{"eval_id":"019dfb14-a085-7b52-8f76-6678f2a4de9c","probe":"How many employees does JPMorganChase have in North America?","golden":"185,208","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185208"}]},{"eval_id":"019dfb14-f2e3-7cee-a27e-79e81867b37a","probe":"How many employees work in CCB?","golden":"144,196","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144196"}]},{"eval_id":"019dfb15-3908-7fc5-93bd-052705ae9929","probe":"In how many countries are JPMorganChase's employees located?","golden":"66","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"}]},{"eval_id":"019dfb15-75a7-7c29-a2ca-90c32df63ac5","probe":"What percentage of total employees are women?","golden":"48%","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48 %"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48 %"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"}]},{"eval_id":"019dfb15-c7c7-74ee-b29b-e7b5d8c9a152","probe":"How many employees work in the Asia-Pacific region?","golden":"96,499","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96499"}]},{"eval_id":"019dfb16-cbe3-7d4d-a23d-2234c2d7d297","probe":"What is the first bulleted item under the list of electronic and internet-based financial solutions?","golden":"lending and other extensions of credit to consumers","png_sha":"704943f48019c6bab8cb509e1ddeb6f9b48085007ac9101976ed3d04798ac274","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"}]},{"eval_id":"019dfb17-0cc4-74a1-8d62-afab29ef1e82","probe":"What is the third bulleted item under the list of electronic and internet-based financial solutions?","golden":"cryptocurrency, including stablecoins","png_sha":"704943f48019c6bab8cb509e1ddeb6f9b48085007ac9101976ed3d04798ac274","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"}]},{"eval_id":"019dfb18-cb9a-7558-a5ce-7b4911abc1ba","probe":"What was the total assets under management in 2025 (in billions)?","golden":"$4,791","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** 4791\n\n**"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791**\n\n**"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4791"}]},{"eval_id":"019dfb19-eada-7639-80c1-d416915f2795","probe":"How many client advisors were there as of December 31, 2025?","golden":"10,150","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150\n\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10150"}]},{"eval_id":"019dfb1a-7fed-744e-a7bc-585de30578fb","probe":"What was the equity assets value in 2025 (in billions)?","golden":"$1,400","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400\n\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1400"}]},{"eval_id":"019dfb1a-d4b4-7ee1-b950-3f3208c24be4","probe":"What was the reported net interest income in 2025 (in millions)?","golden":"$95,443","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95443"}]},{"eval_id":"019dfb1b-4a0a-766a-92cd-c2e37df27c36","probe":"What was the net yield on average interest-earning assets on a managed basis in 2025?","golden":"2.50%","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"}]},{"eval_id":"019dfb1b-9e1c-704c-b958-e7a06540c65f","probe":"What was the Memo: Total Markets net revenue in 2025 (in millions)?","golden":"$35,782","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"}]},{"eval_id":"019dfb1c-4c58-739f-8241-e4a688fff415","probe":"What was the noninterest revenue excluding Markets in 2023 (in millions)?","golden":"$44,361","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44361"}]},{"eval_id":"019dfb1d-0b1b-7540-9211-41f0ac069d15","probe":"In what year was MetLife, Inc. incorporated in Delaware?","golden":"1999","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"}]},{"eval_id":"019dfb1d-fe01-7745-a248-c6531ebdce43","probe":"What act is referenced as the source of the 'forward-looking statements' definition?","golden":"Private Securities Litigation Reform Act of 1995","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"}]},{"eval_id":"019dfb1e-4042-7d24-95d6-9213cb5fb946","probe":"How many factors are listed on this page?","golden":"22","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"}]},{"eval_id":"019dfb1e-d54d-73fd-8f17-16eb21390c86","probe":"What is factor number 10 in the list?","golden":"London Interbank Offered Rate discontinuation and transition to alternative reference rates","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates;"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"}]},{"eval_id":"019dfb1f-5f66-79ad-be34-3c4e429dbcac","probe":"How old is Steven J. Goulart?","golden":"64","png_sha":"8a8df5c53ffc88bd982b700c7adc729d6f1a78da7ebcbf1ee0a1a778e2017590","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"}]},{"eval_id":"019dfb22-1d21-7795-bb3e-bdc661245cb9","probe":"What is the % of Total for Aaa/Aa/A rated securities as of December 31, 2021?","golden":"70.4%","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"}]},{"eval_id":"019dfb23-4f44-7d83-91d3-79100e6cffec","probe":"What were the adjusted earnings available to common shareholders for the U.S. segment?","golden":"$2,996 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"}]},{"eval_id":"019dfb23-8371-717a-825f-6e20e45dcb5f","probe":"What is the U.S. segment's percentage contribution to total segment level adjusted earnings?","golden":"47%","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"}]},{"eval_id":"019dfb23-d976-764b-875f-1c7d8d24b80e","probe":"What were the adjusted earnings for the Asia segment?","golden":"$1,378 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"}]},{"eval_id":"019dfb24-353e-721c-af95-7c83f5c7c811","probe":"What were the adjusted earnings for the EMEA segment?","golden":"$246 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million**\n\n**"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"}]},{"eval_id":"019dfb29-7d6d-77ed-abe1-9e196503fe98","probe":"What is American Life Insurance Company's Moody's rating?","golden":"A1","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1 (5th of 21)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1 (5th of 21)\n\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1 (5th of 21)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1 (5th of 21)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1 (5th of 21)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1 (5th of 21)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"}]},{"eval_id":"019dfb29-d233-7190-9c54-414c50184509","probe":"What is Metropolitan Life Insurance Company's Fitch rating?","golden":"AA-","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"}]},{"eval_id":"019dfb2a-30eb-73bc-9534-9a1a79fcefd9","probe":"What is Metropolitan Tower Life Insurance Company's Moody's rating?","golden":"Aa3","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"}]},{"eval_id":"019dfb3c-0056-7fd4-8497-80ad7e52deed","probe":"What is the date on the letter?","golden":"September 12, 2025","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"}]},{"eval_id":"019dfb3c-443c-749d-9922-e22f48da574a","probe":"What is the total amount of expenses stated in the letter?","golden":"$537.6 billion","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"}]},{"eval_id":"019dfb3c-e409-7e70-93e0-584a7b66e218","probe":"What is the fax number listed at the bottom of the letter?","golden":"916.322.4404","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"}]},{"eval_id":"019dfb3d-df1d-70c3-8680-871f110c4e18","probe":"How many state departments are involved in the ACFR production, according to the letter?","golden":"more than 200","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200"}]},{"eval_id":"019dfb41-090f-742c-a295-a841b0d40942","probe":"What is the last year the ACFR publication target date in March was achieved, according to the letter?","golden":"2018","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"}]},{"eval_id":"019dfb42-0697-72fe-ace9-658c5975fe72","probe":"What is the General fund balance as previously reported on 6/30/2023?","golden":"$64,003,688","png_sha":"4d385e9f1f0ded0edf6cd42e1fce98d308714a9c9a90264d60830da6a87b20a5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64003688"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64003688"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64003688"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64003688"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64003688"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64003688"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 64,003,688"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64003688"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64003688"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64003688"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64003688"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64003688"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64003688"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"}]},{"eval_id":"019dfb42-9508-70e6-ba0b-e32a83de1982","probe":"What is the Pension/OPEB balance as previously reported on 6/30/2023?","golden":"$826,165,564","png_sha":"4d385e9f1f0ded0edf6cd42e1fce98d308714a9c9a90264d60830da6a87b20a5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826165564"}]},{"eval_id":"019dfb45-c922-797e-8c28-c8e8919e6e6b","probe":"What was the General Fund's ending fund balance for fiscal year 2023-24?","golden":"$63.4 billion","png_sha":"be9e4b96b82c2251ae314ddc72ad643547069399fbff67cb23663b4b60410b07","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion"}]},{"eval_id":"019dfb48-c7e6-72a9-8f31-8e936894de0c","probe":"What was the total primary government net position in 2006 (in thousands)?","golden":"$48,552,143","png_sha":"6ded8b72d8724efb0a5addcabb85b9fb055c8702b034b32a8bd9d35ae7b3b2d4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48552143"}]},{"eval_id":"019dfb49-36d0-787d-9b10-263d0dc86158","probe":"What was the total business-type activities net position in 2005 (in thousands)?","golden":"$9,638,143","png_sha":"6ded8b72d8724efb0a5addcabb85b9fb055c8702b034b32a8bd9d35ae7b3b2d4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 9,638,143"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9638143"}]},{"eval_id":"019dfb4a-c5b5-77b8-8666-73fe5ecf7295","probe":"What word appears on the banner above the figure in the seal?","golden":"EUREKA","png_sha":"e78f4e20277a031b7f8a1c8ec01e35359d5db802026c772a280aa46b2e15036d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"}]},{"eval_id":"019dfb4c-a89f-7747-8ca3-fb374afbe129","probe":"How many employees were in the Services industry in 2012?","golden":"6,219,000","png_sha":"ee102138e4471a718761ff29297490e756f20be442c4eab71f74ad7b88ef9337","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"}]},{"eval_id":"019dfb4d-3d6b-7988-bb66-c81ee4e34bf7","probe":"How many employees were in Manufacturing in 2003?","golden":"1,544,500","png_sha":"ee102138e4471a718761ff29297490e756f20be442c4eab71f74ad7b88ef9337","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"}]},{"eval_id":"019dfff9-bbf0-7f8f-9eeb-4283d498732d","probe":"What is the General Fund amount due from primary government to University of California?","golden":"$169,215","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 (in thousands)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169215"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169215"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169215"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215 (amounts in thousands)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169215"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169215"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169215"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169215"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"}]},{"eval_id":"019dfffa-9fa6-7a63-a87b-53eda9047796","probe":"What is the amount from Nonmajor governmental funds due to University of California?","golden":"36,988","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36988\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36988\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36988"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36988"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36988"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36988"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36988"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"}]},{"eval_id":"019dfffb-b244-7a37-903d-2e6addf12282","probe":"What was the net general bonded debt per capita in 2018?","golden":"$2,042","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2042"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2042"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2042"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2042"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2042"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2042"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,042"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2042"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"}]},{"eval_id":"019dfffc-0d62-7f14-a566-4e70db84b399","probe":"What was the net general bonded debt as a percentage of personal income in 2015?","golden":"4.0%","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"}]},{"eval_id":"019dfffc-678a-79c5-aaea-473c3f22a054","probe":"What was the General obligation bonds amount in 2017?","golden":"$79,503,871","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"}]},{"eval_id":"019dfffc-e4bf-79ad-8c4e-89d704ac54ed","probe":"What is at the top of the Texas government structure chart?","golden":"The Electorate","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"}]},{"eval_id":"019dfffe-6b06-706f-a135-e5934397dcc8","probe":"What body sits directly below the Legislature on the chart, alongside the State Auditor's Office?","golden":"Legislative Committees","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"}]},{"eval_id":"019dffff-a90b-7567-a8fa-d73e11996c14","probe":"What body is shown at the very bottom of the Legislative branch chart?","golden":"Sunset Advisory Commission","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"}]},{"eval_id":"019e0000-52c3-755e-9a98-534e00107784","probe":"What is the total pass-through to other agencies?","golden":"$254,334.30","png_sha":"cee789f33becc6e55d762115a7b119808f36099b5c736f4b0ec740bce52a004c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254,334.30\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254,334.30"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254,334.30"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254,334.30"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254,334.30"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"}]},{"eval_id":"019e0001-dddd-7fec-b736-f93ff293500f","probe":"What was the balance in the ESF fund on Aug. 31, 2024?","golden":"$23.8 billion","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"}]},{"eval_id":"019e0002-846c-7a5c-bcd2-21cf9dab8b63","probe":"What was the Texas unemployment rate as of November 2024?","golden":"4.2 percent","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"}]},{"eval_id":"019e0003-4dd3-73ec-8ba4-bf652587ad06","probe":"By how much is Texas' population projected to grow in 2025?","golden":"376,600","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376600"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"}]},{"eval_id":"019e0008-27fa-70f4-8421-41777f7bcace","probe":"What office is shown in pink under the First Deputy Mayor?","golden":"Office of Efficiency","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"}]},{"eval_id":"019e0009-2f8e-768d-8762-ff9e82bcea2b","probe":"What is the SAO Report Number?","golden":"25-316","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"}]},{"eval_id":"019e000b-d49b-7660-82c4-81ecfb04a236","probe":"What percentage of revenue comes from Charges for Services in Graph MDA-6?","golden":"59.7%","png_sha":"3f8e2c78a2134ddb79f740cc731c989a29e5b11d89cdb0254e1f1740d44cfdb0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"}]},{"eval_id":"019e000d-e61a-7a45-b84f-1c881c74e271","probe":"What is the fair value of Private Equity investments (in thousands)?","golden":"$76,309,756","png_sha":"1993d56fb3f7471f5844aa6a62bb8dd9a43b4784dac30f107664bca458bf68ea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"}]},{"eval_id":"019e000e-f859-77f7-aa7c-927c51e130e8","probe":"What is the unfunded commitment for Energy, Natural Resources, Infrastructure (in thousands)?","golden":"$11,460,123","png_sha":"1993d56fb3f7471f5844aa6a62bb8dd9a43b4784dac30f107664bca458bf68ea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11460123"}]},{"eval_id":"019e0010-c825-72aa-a139-0e4ab295b2dc","probe":"What is the minimum aggregate floor area required by the CEP program?","golden":"25,000 square feet","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"}]},{"eval_id":"019e0011-2a92-7ac7-89be-ac4f2296baea","probe":"Under the CRP/CEP programs, by how much were the City's tax revenues reduced in 2024 (in thousands)?","golden":"$12,500","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"}]},{"eval_id":"019e0011-cff1-7126-8235-02b26f0fbab9","probe":"What year did ICAP replace ICIP?","golden":"2008","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"}]},{"eval_id":"019e0017-450f-737d-a346-38c48007c835","probe":"Under the CRP program, what is the per-square-foot dollar amount used in the base abatement calculation formula?","golden":"$2.50","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"}]},{"eval_id":"019e0018-17a0-7847-a0b3-11f039bc48a6","probe":"What is the page number shown at the bottom of this page?","golden":"128","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"}]},{"eval_id":"019e0019-d170-7146-8e38-cc44276e6018","probe":"Under the CRP/CEP programs, by how much were the City's tax revenues reduced as a result of abatement agreement in 2024 (in thousands)?","golden":"$12,500","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12500"}]},{"eval_id":"019e001b-3183-79f1-a745-4e066a6ce3ef","probe":"What is the Executive Order number mentioned in the letter?","golden":"2025-1","png_sha":"781c6fcbd4f3164179bf71cd942ca2e9794fc7c49c6bbcf883dd13f2ce626331","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"}]},{"eval_id":"019e001b-77bc-7c11-843b-51dfbbec15c3","probe":"Who signed this letter?","golden":"Mayor Brandon Johnson","png_sha":"781c6fcbd4f3164179bf71cd942ca2e9794fc7c49c6bbcf883dd13f2ce626331","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"}]},{"eval_id":"019e001d-d405-7881-ab8b-abcb0d7e70e1","probe":"What is Deloitte's fax number listed on the page?","golden":"+1 312 486 1486","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"}]},{"eval_id":"019e0020-bffb-7733-931f-63dac6e0f8f0","probe":"Who is the report addressed to as Mayor?","golden":"Brandon Johnson","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"}]},{"eval_id":"019e0027-f41a-7a7a-b3f6-f9b59cde341b","probe":"What is the experience study period for the Policemen's plan?","golden":"January 1, 2019 - December 31, 2023","png_sha":"2aded5f520cbaa023e8d0c1e94f15e68ccafa9f34d1e6736781e6f894512fe8e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"}]},{"eval_id":"019e0028-b45f-7292-959c-f04db8d08d19","probe":"What is the experience study period for the Laborers' plan?","golden":"January 1, 2017 - December 31, 2019","png_sha":"2aded5f520cbaa023e8d0c1e94f15e68ccafa9f34d1e6736781e6f894512fe8e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"}]},{"eval_id":"019e002e-34d1-7c51-ba48-bffeca76fb26","probe":"What was the loans receivable balance of the CCCF as of December 31, 2024?","golden":"$3.1 million","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million"}]},{"eval_id":"019e002e-ef48-7527-8160-cb77c6e44245","probe":"On what date did the City of Chicago City Council adopt the ordinance organizing the STSC?","golden":"October 11, 2017","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"}]},{"eval_id":"019e0030-d1da-7720-bec1-d70663e3456a","probe":"On what date did the City Council adopt the CCCF Ordinance?","golden":"November 16, 2016","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"}]},{"eval_id":"019e0033-8f40-79d7-8505-50112ded8060","probe":"What is the website where complete financial statements of the STSC can be obtained?","golden":"www.salestaxsecuritizationcorporation.com","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"}]},{"eval_id":"019e003a-5da3-7d08-9f15-665248ccb0cf","probe":"What was the final budgeted Vehicle Tax amount under Transportation Tax (in thousands)?","golden":"$128,777","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128777"}]},{"eval_id":"019e003a-e619-7c9f-b4b2-aa2807d3bff9","probe":"What was the actual Motor Fuel Tax and Project revenue under Transportation Tax (in thousands)?","golden":"$122,483","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122483"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"}]},{"eval_id":"019e003c-6cc9-782c-bca0-875bef94c76c","probe":"What was the final budgeted MEABF Pension Reserve under Special Area and Utility Taxes (in thousands)?","golden":"$216,275","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216275"}]},{"eval_id":"019e003d-55d2-7007-b3b6-dc37892643d2","probe":"Who is the Chief Actuary?","golden":"Marek Tyszkiewicz","png_sha":"89c77daf9c6f881f0116f445cbf736cffc12698b60a93b437699a1a075b00138","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"}]},{"eval_id":"019e003f-44df-7a8d-a15c-ff2dc3cf553b","probe":"What is the funded ratio for the 2022 valuation date?","golden":"85.1%","png_sha":"13c08f8d02fa78d2fc1f1b9783d494af4a43f3083f75509ffac06a9ae415320f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"}]},{"eval_id":"019e0040-0266-795a-b6d2-549f195f8032","probe":"What percentage of the Police Superior Officers' Variable Supplements Fund is held in Collective Trust Funds?","golden":"59.28%","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%**  \n**"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"}]},{"eval_id":"019e0040-6668-7abd-8cd8-dd05d069c1c1","probe":"What is the dollar amount of Equity Securities in the Police Officers' Variable Supplements Fund?","golden":"$771,119","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"771119"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"771119"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"771119"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"771119"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"771119"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"771119"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"}]},{"eval_id":"019e0041-2237-71d4-8880-cb8564c7b0ae","probe":"What is the dollar amount of Short-Term Investments in the Police Superior Officers' Variable Supplements Fund?","golden":"$8,441","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"}]},{"eval_id":"019e0042-1c07-71d9-8683-e990abab4862","probe":"What is the Reduced Service Retirement probability at 20 years of service?","golden":"5.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"}]},{"eval_id":"019e0043-db39-746e-8a90-d9b8e9e16e2f","probe":"What is the Unreduced Before Full Escalation probability at 22 years of service?","golden":"5.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"}]},{"eval_id":"019e0044-11fe-7039-99f0-4014e1cca342","probe":"What is the Reduced Service Retirement probability at 21 years of service?","golden":"2.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"}]},{"eval_id":"019e0045-18ce-7ff9-90d3-7a8a76d3a7b2","probe":"What is the As Restated Total Liabilities amount?","golden":"54,689,670","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54689670\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54689670"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54689670"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54689670"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54689670"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"}]},{"eval_id":"019e0046-8a1d-76f7-a894-dfdf17c5e779","probe":"What is the As Previously Stated Unrestricted (Deficit) amount (in thousands of dollars)?","golden":"(33,888,893)","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"}]},{"eval_id":"019e0048-5d8d-7e41-bfac-807538f6bc7d","probe":"What is the required year of adoption for GASB Statement No. 102?","golden":"2025","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"}]},{"eval_id":"019e0049-7334-7204-a87d-cdd77f11d1df","probe":"What is the As Restated Total Net (Deficit)/Position amount (in thousands)?","golden":"$(30,877,248)","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"}]},{"eval_id":"019e004a-3183-7f93-ae28-888547cf9f69","probe":"What is the As Previously Stated Accrued and Other Liabilities amount (in thousands)?","golden":"$2,037,352","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2037352\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2037352"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2037352"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2037352"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2037352"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2037352"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2037352"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2037352"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2037352"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2037352"}]},{"eval_id":"019e004b-c349-7e93-af8d-24a8c0227413","probe":"Who is the Chairman of the Texas Transportation Commission?","golden":"J. Bruce Bugg, Jr.","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."}]},{"eval_id":"019e004c-1788-7c26-832d-effce8fee9e9","probe":"What city is Commissioner Robert C. Vaughn from?","golden":"Dallas","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"}]},{"eval_id":"019e004c-7b29-737b-b3c2-4cb5677b686a","probe":"What city is Commissioner Steven D. Alvis from?","golden":"Houston","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"}]},{"eval_id":"019e004e-6fac-7e8f-a9ed-7aab75af118d","probe":"What is the Total Foreign Currency Risk for Fiduciary Funds (in thousands)?","golden":"$454,100","png_sha":"14dd94971a85d5333d42a72d87ae42c4f4cf19684f10114f6d12e3dc0dcfbba3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"}]},{"eval_id":"019e004f-570b-7494-b4dc-1980043719cb","probe":"What is the Component Units amount for Uninsured and Uncollateralized in Table 3A (in thousands)?","golden":"$729,847","png_sha":"14dd94971a85d5333d42a72d87ae42c4f4cf19684f10114f6d12e3dc0dcfbba3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729847"}]},{"eval_id":"019e0050-7b43-7b4a-b132-8ba0d44ecc08","probe":"What is the Total Fund Balance \u2013 Governmental Funds (in thousands)?","golden":"$98,174,085","png_sha":"2e5b15b0fe9ca40f66bc4f99fea40f7e0fb26c9abe4ac75ea6dad2ab72ae36d6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98,174,085"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98174085"}]},{"eval_id":"019e007c-e48c-710f-9404-90a2a810ccb4","probe":"What is the Net Position of Governmental Activities (in thousands)?","golden":"$134,878,410","png_sha":"2e5b15b0fe9ca40f66bc4f99fea40f7e0fb26c9abe4ac75ea6dad2ab72ae36d6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134878410"}]},{"eval_id":"019e007d-9a24-752a-89d4-7fe852700caa","probe":"What is the total revenue shown in the Revenue by Source pie chart?","golden":"$190.5 Billion","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"}]},{"eval_id":"019e007e-1a80-7e4b-98c2-9c3f2d812c06","probe":"What percentage of revenue came from Taxes?","golden":"42.7%","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"}]},{"eval_id":"019e007e-5b89-72a2-b531-375ac7e4ca75","probe":"What is the dollar amount of Operating Grants and Contributions?","golden":"$74.9 billion","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"}]},{"eval_id":"019e007e-aac9-7785-8c44-edb9f9dfe20d","probe":"What are the total expenses across all governmental activities?","golden":"$154,896","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 (millions)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"}]},{"eval_id":"019e007f-3589-7306-b64b-6253528585e4","probe":"What page is Risk Factors on?","golden":"14","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"}]},{"eval_id":"019e007f-7683-7d10-a251-ff6bdde0aca0","probe":"What page is Executive Compensation on?","golden":"105","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"}]},{"eval_id":"019e007f-b345-710c-b63d-5812e55e82ef","probe":"What page is Financial Statements and Supplementary Data on?","golden":"48","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"}]},{"eval_id":"019e0080-81ba-7bac-bba1-8cc2e8324436","probe":"What page is the Budgetary Comparison \u2013 General Fund on?","golden":"47","png_sha":"0a460adc7db810670c579dc36d27c02a4097bb3e02f77fbbeacd84bbcc9d2f0e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"}]},{"eval_id":"019e0080-b0bf-7f30-a02e-a2ed8dcea371","probe":"What page is the Schedule of Employee Benefits \u2013 All Funds on?","golden":"56","png_sha":"0a460adc7db810670c579dc36d27c02a4097bb3e02f77fbbeacd84bbcc9d2f0e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"}]},{"eval_id":"019e0081-ed0a-7c3a-a9ba-53b6b5920008","probe":"What word is shown as a watermark across the map?","golden":"DRAFT","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"}]},{"eval_id":"019e0083-0a96-77f4-a106-fb583482c798","probe":"How much did the General Land Office (GLO) increase?","golden":"$860 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"}]},{"eval_id":"019e0083-5461-7354-8851-9512e63b1c22","probe":"How much did the Texas Commission on Environmental Quality (TCEQ) increase?","golden":"$543 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand increase\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand increase\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand increase"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand increase"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand increase"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"}]},{"eval_id":"019e0083-c942-7b97-83f8-c0423a20e2a4","probe":"How much did the Federal Emergency Management Agency (FEMA) decrease?","golden":"$420 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"}]},{"eval_id":"019e0084-65de-77d8-92f6-79df23bc1fad","probe":"What is the phone number for Pattillo, Brown & Hill, L.L.P.?","golden":"254.772.4901","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"}]},{"eval_id":"019e0084-dffc-7ecf-b0c1-44b81836ebdd","probe":"What is the date of the year ended for the audit?","golden":"September 30, 2024","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"}]},{"eval_id":"019e009f-5030-795d-b32e-68b8c8725b1a","probe":"What is the page number shown at the bottom right?","golden":"H261","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261"}]},{"eval_id":"019e00a0-6d47-7a01-8cdb-9db00cf90181","probe":"Which bill number is referenced as the 'Born-Alive Abortion Survivors Protection Act'?","golden":"H.R. 21","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21"}]},{"eval_id":"019e00a2-46eb-7c4d-93dc-be4b015c5931","probe":"Until what time may morning-hour debate continue?","golden":"11:50 a.m.","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."}]},{"eval_id":"019e00a2-8827-7350-ac1d-d1e691c7bc93","probe":"Which Congress's proceedings does this issue cover?","golden":"119th","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress (first session)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress (first session)\n\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress (first session)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress (first session)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress (first session)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress (1st session)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress (first session)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress (first session)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress (first session)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress (first session)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress (first session)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress (first session)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"}]},{"eval_id":"019e00a3-4654-7104-90ff-d36264aea63f","probe":"Who did Speaker Mike Johnson appoint as Speaker pro tempore for the day?","golden":"Nathaniel Moran","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran (Hon. Nathaniel Moran)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the Honorable NATHANIEL MORAN\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran (Mr. Moran)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the Honorable Nathaniel Moran\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran (Hon. Nathaniel Moran)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the Honorable NATHANIEL MORAN"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hon. Nathaniel Moran"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran (Mr. Moran)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hon. Nathaniel Moran"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hon. Nathaniel Moran"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable NATHANIEL MORAN"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran (Mr. Moran)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran (Hon. Nathaniel Moran)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hon. Nathaniel Moran"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable NATHANIEL MORAN"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honorable Nathaniel Moran (Mr. MORAN)"}]},{"eval_id":"019e00a4-39cf-73f5-a08d-bdaf6f0e9555","probe":"Which state is Mrs. Trahan from?","golden":"Massachusetts","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"}]},{"eval_id":"019e00a4-9927-7270-b177-688639d2d84a","probe":"Which state is Mr. Thompson from?","golden":"Pennsylvania","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"}]},{"eval_id":"019e00a5-86fd-7ef3-9421-534e8a66b6ef","probe":"How many 'yeas' were there in Roll No. 20?","golden":"214","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"}]},{"eval_id":"019e00a5-ff31-72d6-b137-910bed3336e6","probe":"How many representatives were 'not voting' in Roll No. 20?","golden":"15","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15**  \n**"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"}]},{"eval_id":"019e00a6-329c-73a0-9a01-cd95583196e9","probe":"How many 'nays' were there in Roll No. 20?","golden":"204","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"}]},{"eval_id":"019e00a7-701e-7774-bdaa-4a60fe45e545","probe":"What is the page number shown at the top left?","golden":"H276","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"}]},{"eval_id":"019e00a7-fb7c-797d-8520-954d5503a748","probe":"What is the Roll number for the vote shown on this page?","golden":"20","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"}]},{"eval_id":"019e00ac-04dd-7f1d-bcec-9be7f5c1f3ce","probe":"Did Aderholt vote yea or nay?","golden":"yea","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"}]},{"eval_id":"019e00ad-d3ed-7216-853a-30e02dbd1131","probe":"Who is the first name listed alphabetically in the NAYS column?","golden":"Adams","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"}]},{"eval_id":"019e00b0-cecb-7e7c-8149-7640c1dad861","probe":"Which member changed their vote from \"nay\" to \"yea\"?","golden":"Mr. Palmer","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"}]},{"eval_id":"019e00b3-c235-73fb-ba21-0118c8eadbf3","probe":"What is the page number shown in the top-left corner?","golden":"S250","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"}]},{"eval_id":"019e00b4-9c27-73de-8223-11187c914c6f","probe":"What is the date shown at the top-right of the page?","golden":"January 20, 2025","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"}]},{"eval_id":"019e00b9-b13c-7e4a-bf11-475eea29d6d3","probe":"Did Senator McConnell vote yea or nay on the final passage of S. 5?","golden":"yea","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** yea\n\n**"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"}]},{"eval_id":"019e00bb-59ee-702a-8cec-38e372b26db8","probe":"How many senators voted YEA on Amendment No. 8?","golden":"75","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"}]},{"eval_id":"019e00bb-a83a-79e5-808d-25352081e864","probe":"How many senators voted NAY on the final passage of S. 5?","golden":"35","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"}]},{"eval_id":"019e00bc-df61-7504-ab8f-56af050077d7","probe":"Who is being considered for Secretary of State on Executive Calendar No. 2?","golden":"Marco Rubio","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio (of Florida)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio (of Florida)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio (of Florida)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio (of Florida)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO of Florida"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio (of Florida)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio (of Florida)"}]},{"eval_id":"019e00bf-a471-719a-84c8-972702dced95","probe":"What dollar amount is mentioned as the threshold for financial harm to a State or its residents?","golden":"$100","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"}]},{"eval_id":"019e00c1-687b-7e30-917e-677d5c514e5a","probe":"Who asked for the yeas and nays on the vote for S. 5?","golden":"Mrs. Britt","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT  \n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT"}]},{"eval_id":"019e00c1-d9d4-7426-9471-e13471bf2c6f","probe":"How many nays were there on the vote on Amendment No. 8?","golden":"24","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"}]},{"eval_id":"019e00c6-1e73-73ec-8e95-413c88e39426","probe":"How much did the Wesley Hunt Victory Fund contribute on 2/3/2025?","golden":"$25,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00"}]},{"eval_id":"019e00c6-5871-7da2-a93b-3aefb5c66f16","probe":"What is the page number shown at the top left?","golden":"S2714","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"}]},{"eval_id":"019e00c8-3f2a-7e4f-b0e4-86c796356894","probe":"How much did the Connecticut Republican State Central Committee transfer on 9/27/2024?","golden":"$10,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"}]},{"eval_id":"019e00c9-c213-7e12-b66f-043b2559c706","probe":"Who is being nominated to be Lieutenant Commander in the Coast Guard?","golden":"John O. Mansolillo","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"}]},{"eval_id":"019e00ce-9d49-7844-bd6c-346e75c0b284","probe":"What is the bill number for the bill to direct the Secretary of the Treasury to stop minting the penny?","golden":"S. 1525","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"}]},{"eval_id":"019e0518-b40f-7b97-99f0-2cd141711ff0","probe":"What is the bill number for the bill to regulate assault weapons?","golden":"S. 1531","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531"}]},{"eval_id":"019e051c-6f18-78b3-a1d7-9d8a0a2b9618","probe":"How many senators voted yea on the Driscoll nomination?","golden":"66","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"}]},{"eval_id":"019e051d-3c27-7462-be35-0be6eece26b9","probe":"How many senators were listed as NOT VOTING?","golden":"6","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"}]},{"eval_id":"019e051d-a887-715d-88bf-933cc563b087","probe":"How many nays were there in the vote?","golden":"28","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"}]},{"eval_id":"019e051e-38d3-7d68-9805-50585c912e12","probe":"How would Senator Cruz of Texas have voted if present?","golden":"yea","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea (in favor of confirming the nomination)\n\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea (yes)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea (on Driscoll nomination)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea (yes)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"}]},{"eval_id":"019e0520-d920-72fd-9146-7ff4401c225d","probe":"Did Senator Booker vote yea or nay on the Driscoll nomination?","golden":"nay","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"}]},{"eval_id":"019e0523-07a2-7eed-a522-32a019057e4b","probe":"Under what clause and rule were sponsors added to public bills?","golden":"clause 7 of rule XII","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"}]},{"eval_id":"019e0524-2f26-7e2d-b1d6-9d9e4787d2c7","probe":"How many additional sponsors were added to H.R. 21?","golden":"8","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"}]},{"eval_id":"019e0525-2888-7fab-bbe4-24c066ee419f","probe":"Who was added as a sponsor to H.R. 31?","golden":"Mr. Stauber","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER"}]},{"eval_id":"019e0529-025b-7daa-a5e9-a453809b33ba","probe":"How many sponsors were added to H. Res. 23?","golden":"15","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"}]},{"eval_id":"019e053e-4d48-7017-b80c-96993dddb76d","probe":"How many patients were in the SOC alone group?","golden":"4,321","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"}]},{"eval_id":"019e053f-1f3f-7cd4-9bdf-bb8319b59261","probe":"What is the table number and title?","golden":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"}]},{"eval_id":"019e0540-facb-7b6a-8fd8-3f509341da68","probe":"What was the mean age of participants in the RECOVERY trial?","golden":"66 years","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"}]},{"eval_id":"019e0541-5acc-73a2-a0f0-4a8a3fd3f3d7","probe":"When was this table last updated?","golden":"February 29, 2024","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"}]},{"eval_id":"019e0542-7270-77f1-aa19-55066dadd841","probe":"How many patients were in the SOC alone group?","golden":"4,321","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4321"}]},{"eval_id":"019e0543-15cb-749c-890f-dc25b546fa1f","probe":"What percentage of participants had laboratory-confirmed SARS-CoV-2 infection?","golden":"89%","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"}]},{"eval_id":"019e0547-98af-7c91-aa30-6a7096eca524","probe":"What is the table number and title shown at the top of the page?","golden":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"}]},{"eval_id":"019e0547-eecc-7d07-95de-24c48450b6a5","probe":"On what date was this document downloaded according to the bottom of the page?","golden":"3/1/2024","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"}]},{"eval_id":"019e0549-117f-704c-b2ed-3771bcbf57de","probe":"What is the URL shown at the bottom of the page where this document was downloaded from?","golden":"https://www.covid19treatmentguidelines.nih.gov/","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"}]},{"eval_id":"019e054a-48f1-7ae1-8c9a-f98de9d0fa5b","probe":"What is the recommendation for patients hospitalized but not requiring supplemental oxygen who are at high risk of progressing to severe COVID-19?","golden":"Remdesivir","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir\u1d48 (BIIb) for immunocompromised; (BIII) for other high-risk patients\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir^d (BIIb) for immunocompromised pts; (BIII) for other high-risk pts\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk pts\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised pts; (BIII) for other high-risk pts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** Remdesivir (BIIb) for immunocompromised pts; (BIII) for other high-risk pts\n\n**"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised pts; (BIII) for other high-risk pts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir^d (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir\u1d48 (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir\u1d48 (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir\u1d48 (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for immunocompromised; (BIII) for other high-risk patients"}]},{"eval_id":"019e0550-1990-7266-9919-560f19c4cee5","probe":"In the CATCO trial, what percentage of patients received corticosteroids?","golden":"87%","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"}]},{"eval_id":"019e0553-86d1-71ca-b900-5bbaabb7ca45","probe":"How many randomized controlled trials were included in the pooled analysis of individual data mentioned with ACTT-1?","golden":"9","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"}]},{"eval_id":"019e055a-07af-77a5-89c9-42e3d3fa137d","probe":"What is the maximum daily dose of low-dose aspirin?","golden":"81 mg","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"}]},{"eval_id":"019e055a-a680-7323-8d08-3ac187ccf89f","probe":"What is the rating for IVIG monotherapy when glucocorticoids are contraindicated?","golden":"BIIb","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(BIIb)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(BIIb)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(BIIb)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(BIIb)"}]},{"eval_id":"019e055d-286a-7563-a7e4-fcf6471dab8b","probe":"What is the dose of infliximab listed for intensification therapy?","golden":"5\u201310 mg/kg IV for 1 dose","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"}]},{"eval_id":"019e055e-28ea-7f76-943f-b37787cd73cb","probe":"What is the IV dose range for high-dose anakinra?","golden":"5\u201310 mg/kg/day","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day"}]},{"eval_id":"019e055f-16e9-7882-9aa1-55c4030f9893","probe":"According to footnote c, in which patients should infliximab NOT be used?","golden":"patients with macrophage activation syndrome","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"}]},{"eval_id":"019e055f-c91a-7e0f-9401-67c36bb17b91","probe":"According to the Key, what does CAA stand for?","golden":"coronary artery aneurysm","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"}]},{"eval_id":"019e0561-73ca-7c46-9bf0-5c643e61cde3","probe":"What does IBW stand for according to the Key?","golden":"ideal body weight","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight"}]},{"eval_id":"019e05a9-4840-7d85-a06e-f789e706a095","probe":"What is the risk level for patients with mild asthma, overweight, or well-controlled diabetes?","golden":"Low","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"}]},{"eval_id":"019e05ab-8ba2-7ab7-87ce-36b3ba6a8e47","probe":"What is the risk level shown for patients with sickle cell disease or chronic kidney disease?","golden":"Intermediate","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"}]},{"eval_id":"019e05ad-fd6c-7734-88ed-1ec50c394ff9","probe":"How many conditions are listed under \"Strong or Consistent Association With Progression to Severe COVID-19\"?","golden":"8","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8**  \n**"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"}]},{"eval_id":"019e05b0-6eee-79fe-9c1a-85e69f5d1b78","probe":"What is the page number?","golden":"174","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"}]},{"eval_id":"019e05b0-9f88-7493-8093-1faf321a65c1","probe":"What is the date the document was downloaded?","golden":"3/1/2024","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"}]},{"eval_id":"019e05b0-d9cd-707e-a8fc-05816b33e002","probe":"What is the title of this section shown in the orange header?","golden":"Summary Recommendations, continued","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"}]},{"eval_id":"019e05ba-b872-7e8f-9ab0-ebf540496835","probe":"How many people were in the placebo group?","golden":"761","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"}]},{"eval_id":"019e05bd-b79d-79ce-83a2-61bee82f41bd","probe":"What was the mean age of participants?","golden":"58 years","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"}]},{"eval_id":"019e05bd-fce1-7c37-9985-6a2be13c70b5","probe":"What percentage of participants received corticosteroids?","golden":"79%","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"}]},{"eval_id":"019e05bf-8d4e-7984-b130-f857ef177151","probe":"What is Pablo Tebas's financial disclosure relationship with Shionogi?","golden":"Consultant","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"}]},{"eval_id":"019e05c0-2875-7f53-8cd2-1afd5c604eef","probe":"What is Andrew T. Pavia's relationship with Haleon?","golden":"Honoraria","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"}]},{"eval_id":"019e05c1-9d7a-7ef6-8d4a-75d9a4d8bc53","probe":"What is Grant Schulert's financial disclosure relationship with Boehringer Ingelheim?","golden":"Consultant","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"}]},{"eval_id":"019e05c2-9694-7119-b6c6-e2863ab93d51","probe":"What company is Phyllis Tien disclosed as receiving research support from?","golden":"Merck","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"}]},{"eval_id":"019e05c3-4ee4-7de9-abf1-e04c45c9b57f","probe":"What is Susan Swindells's financial disclosure relationship with GSK/ViiV Healthcare?","golden":"Research support","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"}]},{"eval_id":"019e05e7-8068-7743-a656-13b1d4d4190b","probe":"How many chapter objectives are listed on this page?","golden":"5","png_sha":"4fb66d797829b4efe7d38ed6d367871d6664885f70ef83a42d3f0dfec31552e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e05f2-f42c-7018-ab71-30b51adf12e2","probe":"What is the name of the region located between the right and left lumbar regions?","golden":"Umbilical region","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"umbilical region  \n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"umbilical region\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"umbilical region\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"umbilical region\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"umbilical region"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"umbilical region"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"umbilical region"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"umbilical region"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"umbilical region"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"umbilical region"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"umbilical region"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"umbilical region"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"}]},{"eval_id":"019e05f3-f4bd-74db-9544-35cd14788275","probe":"What is the name of the region directly above the umbilical region?","golden":"Epigastric region","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"epigastric region"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"}]},{"eval_id":"019e05f6-e2c6-7b53-b37c-1808bd28b0d4","probe":"What organ is shown as the example at the Organ level in the pyramid?","golden":"Bladder","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder"}]},{"eval_id":"019e05f7-dd30-7195-830e-cd261e20c2b7","probe":"What organ system is shown as the example at the Organ system level?","golden":"Urinary tract system","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system (kidney/ureter/bladder/urethra)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"gan system shown as the example at the Organ system level is the urinary system (also labeled \"Urinary tract system\").\n\n**"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary system (urinary tract system)**  \n**"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system (kidney/ureter/bladder/urethra)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system (urinary system)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system (kidney/ureter/bladder/urethra)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system (urinary system)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system (kidney/ureter/bladder/urethra)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system (kidney/ureter/bladder/urethra)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system (urinary system)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"urinary tract system (urinary system)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"}]},{"eval_id":"019e05f9-174d-779b-8451-840365bb3ab1","probe":"What type of muscle cell is shown at the Cellular level in the pyramid?","golden":"Smooth muscle cell","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell\n\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"smooth muscle cell"}]},{"eval_id":"019e05fa-5cd7-7bf5-ad75-0aa2f060da1e","probe":"What is the name of the plane shown at the bottom of the figure, near the body's feet?","golden":"Oblique plane","png_sha":"d0de1bb560e9b722942304e532a14882201f7692dbe44333b38e37a146f08834","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"oblique plane\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"oblique plane"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"oblique plane"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"oblique plane"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"}]},{"eval_id":"019e0a71-d77a-7463-8c88-e70ccbeb93a7","probe":"How many electrons are shown in the cloud of negative charge?","golden":"2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"}]},{"eval_id":"019e0a77-521b-7c1e-96e5-0fcfd2acccfb","probe":"How many positive charges are shown in the nucleus of the electron cloud model?","golden":"2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2**\n\n**"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"}]},{"eval_id":"019e0a78-60c3-7ff1-a58d-36cf79d83532","probe":"What is the pH of blood?","golden":"7.4","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"}]},{"eval_id":"019e0a78-c1e6-7be1-b2ed-7370055ce7a4","probe":"What is the pH of baking soda?","golden":"9.5","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"}]},{"eval_id":"019e0a79-38e3-7203-9d9c-b65c2c843999","probe":"What is the pH of black coffee?","golden":"5","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e0a7f-36c1-76f1-9b7d-a75d3f8b57bc","probe":"What are the regions of the enzyme called where substrates bind?","golden":"Active sites","png_sha":"56f42b1466f0ba4fd23da4bdafef8224d214d10ff10aa671d80ddc4389ea94dd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"}]},{"eval_id":"019e0a7f-f372-7caa-bdd1-9371e7bc0c6a","probe":"How many chromosomes does the page say are inside the nucleus of each cell?","golden":"46","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"}]},{"eval_id":"019e0a80-2d48-78ae-9837-df877d92d50a","probe":"Approximately how many genes do humans have in their DNA according to this page?","golden":"22,000","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000"}]},{"eval_id":"019e0a80-c197-7fce-a219-ddb90e59c15f","probe":"What color represents Guanine in the diagram?","golden":"Blue","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"}]},{"eval_id":"019e0a81-1a13-7011-bf33-0b2b8c97db32","probe":"What color represents Adenine in the diagram?","golden":"Red","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"}]},{"eval_id":"019e0a83-ca15-7698-adf8-be9e8fecc270","probe":"What is labeled as the area inside the cell in the large membrane illustration?","golden":"Intracellular","png_sha":"a2c418cbcdc6704d925ad4ffdd78dee38a58fc1ea68774d0094b65c486a66bf8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular**  \n**"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** Intracellular  \n**"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"}]},{"eval_id":"019e0a8c-68fb-7f92-a952-b3faa7d123a4","probe":"What is the chapter title shown in the header at the top of the page?","golden":"Cell Membrane","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"}]},{"eval_id":"019e0a91-e6fb-79fb-b85f-ccfa87b7f449","probe":"What is labeled above the lipid bilayer in the center of the diagram?","golden":"Extracellular fluid","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"}]},{"eval_id":"019e0a92-7404-7aab-b271-b5cbb06491b3","probe":"What is labeled below the lipid bilayer in the center of the diagram?","golden":"Cytoplasm","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"}]},{"eval_id":"019e0a94-7773-7d3d-b4db-4925da2a4c81","probe":"What are the three labels above the cell images in Figure 3.1.6?","golden":"Hypertonic, Isotonic, Hypotonic","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic Isotonic Hypotonic"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic Isotonic Hypotonic"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic Isotonic Hypotonic"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic Isotonic Hypotonic"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic Isotonic Hypotonic"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic Isotonic Hypotonic"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic Isotonic Hypotonic"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic Isotonic Hypotonic"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"}]},{"eval_id":"019e0aa6-cdb4-70a0-951f-040144680d97","probe":"What is labeled in purple at the center of the diagram?","golden":"Crystalline core","png_sha":"29f66040d5b404ad4868b569f57abcbd771a080fa8fcc185a3187093b4d3defb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"}]},{"eval_id":"019e0ab1-a72f-70b0-9619-a8e2a81fee46","probe":"What are the four nitrogenous bases listed in the legend?","golden":"Adenine, Thymine, Guanine, Cytosine","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"}]},{"eval_id":"019e0ab3-3b2c-7cf7-9e5a-87076b99eb2f","probe":"What color is used to represent Guanine in the legend?","golden":"Blue","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"}]},{"eval_id":"019e0ab4-5e27-7fa0-bdb3-55833bf40f16","probe":"What type of bonds connect the two DNA strands together according to the diagram?","golden":"Hydrogen bonds","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds"}]},{"eval_id":"019e0ac6-e7e3-7800-ac52-eee064e4e8b7","probe":"What is the scale bar length shown in the microscope images?","golden":"5 \u03bcm","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"}]},{"eval_id":"019e0ac7-674b-7f8f-ac85-ce02731c302a","probe":"How many stages are shown in the diagram at the top of the page?","golden":"6","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"}]},{"eval_id":"019e0ac8-36ba-7365-9435-ec92bf202c05","probe":"According to figure 3.5.3, what is the first phase of mitosis?","golden":"Prophase","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"}]},{"eval_id":"019e0ac9-ab1a-7551-88fe-ba669d0ab987","probe":"What is the last stage shown in the cell division diagram (after telophase)?","golden":"Cytokinesis","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"}]},{"eval_id":"019e0ad3-52d5-7f4c-8d3d-591d2476cefd","probe":"What is at the very top of the stem cell differentiation diagram?","golden":"Totipotent embryonic stem cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"}]},{"eval_id":"019e0adb-d424-739a-88c3-a9c6837b69aa","probe":"What type of stem cell is at the top of the diagram?","golden":"Totipotent embryonic stem cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"}]},{"eval_id":"019e0ae7-f32b-7670-af77-ced5432c5f69","probe":"What specialized cell type is shown between 'Heart muscle' and 'Skin' in the bottom row?","golden":"Red blood cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red blood cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"}]},{"eval_id":"019e0b0b-0842-7562-aaee-a34590209d11","probe":"What is the figure title for Figure 4.6.2?","golden":"Development of Cancer","png_sha":"c97dbfb9dac36762398856cdab61d5779eae44284b94b744c8e56704bbf954e8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"}]},{"eval_id":"019e0b35-2b57-7c4e-9af5-fa094b59bb2c","probe":"What cell type is shown in the bottom-right image of the diagram?","golden":"Pancreatic cell","png_sha":"7b24760285552c0a3e2beb4a713373cf7079657b1996b630c4cab49bb81d2a0c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"}]},{"eval_id":"019e0eaf-c1cd-797e-834b-863d872f236e","probe":"What cell type is shown in the bottom-left image of the diagram?","golden":"Lung cell","png_sha":"7b24760285552c0a3e2beb4a713373cf7079657b1996b630c4cab49bb81d2a0c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"}]},{"eval_id":"019e0eb0-b4d4-72a3-99bd-8214864274dd","probe":"Which long bone is shown as the example in the diagram?","golden":"Femur","png_sha":"649d7b93ee3bd97ec82fa0d6dc7eb1ef1d3a531661aaf8e5a64a2e776e7befdf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"femur\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"femur"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"}]},{"eval_id":"019e0eb5-35af-7967-8d48-00aa0aa1a645","probe":"According to table 11.4, what is the origin of the superior oblique?","golden":"Sphenoid bone","png_sha":"e52a483f3e3402fc6874a991f546b566e2a6a0e32ba17df2ef455c46bc8e0793","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"}]},{"eval_id":"019e0eb7-fc68-7c2e-ad2c-3675d09c8aa1","probe":"What color represents the appendicular skeleton in the diagram's key?","golden":"Purple","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (or violet/blue-purple)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (or blue-purple)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (or lavender)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (lavender/blue-violet)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (or light purple)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (or blue-purple)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (or blue-purple)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (or lavender)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (or blue-purple)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (lavender shade)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (or blue-purple)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (lavender/blue-purple)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (or blue-purple)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (lavender/blue-purple)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (or lavender/blue)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (darker shade)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple (lavender)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"}]},{"eval_id":"019e0eb9-c545-743f-b1c1-6053776f3ffb","probe":"What bone is labeled directly below the Humerus on the arm?","golden":"Ulna","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna**  \n**"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna**  \n**"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna**  \n**"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna**  \n**"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ulna**  \n**"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna**  \n**"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna**  \n**"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna**  \n**"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna**  \n**"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna**  \n**"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"}]},{"eval_id":"019e0eba-022c-7bba-8967-31ab884feb4d","probe":"What is the bone labeled directly below the Femur in the diagram?","golden":"Patella","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"}]},{"eval_id":"019e0eba-8701-7de9-8ba9-578294d6b194","probe":"What is the bone labeled directly between the Clavicle and the Thoracic cage?","golden":"Scapula","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula**  \n**"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula  \n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula**  \n**"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula**  \n**"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula**  \n**"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula**  \n**"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula**  \n**"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula**  \n**"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"}]},{"eval_id":"019e0ebd-9465-739b-8454-3efaee4d4310","probe":"What is the label directly below 'Rotator brevis' in the Deep spinal muscles diagram?","golden":"Rotator longus","png_sha":"8267a338f131676cd4f156eb0c4a18c6d48352ad7a386fd12707e7503673af3f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus**  \n**"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus**  \n**"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus**  \n**"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"}]},{"eval_id":"019e0ebf-4889-76bf-9d21-fdeaa9903ac1","probe":"On the left hand side of the left lateral view, what muscle is labeled directly above the Anterior scalene?","golden":"Medial scalene","png_sha":"8267a338f131676cd4f156eb0c4a18c6d48352ad7a386fd12707e7503673af3f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene**  \n**"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene**  \n**"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"}]},{"eval_id":"019e0ec1-bc36-7c2e-a816-0d61d873fe40","probe":"What file name is shown in the WebScope micrograph?","golden":"054 - Peripheral nerve_001.svs","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"}]},{"eval_id":"019e0eca-119a-763f-ac56-f38e33c22003","probe":"What four carpal bones are labeled in the figure 8.2.5?","golden":"Hamate, Trapezoid, Trapezium, Capitate","png_sha":"306e13b6e12dfea3dcc83ac66671b7f4f26e03a8658a38703694470c4b84acff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"}]},{"eval_id":"019e0ecc-c17a-7df3-a1f4-407930ed7366","probe":"How many distinct structures are labeled with leader lines on this figure?","golden":"5","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5**  \n**"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5**  \n**"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5**  \n**"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e0ecd-0967-77f3-a1b2-140685a06b07","probe":"What structure is labeled at the very top of the cell?","golden":"Microvilli","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** Microvilli\n\n**"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"}]},{"eval_id":"019e0ecd-62a5-7179-841c-8e4ba5c98a0a","probe":"What structure is labeled at the very bottom of the cell?","golden":"Nucleus","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** Nucleus  \n**"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"}]},{"eval_id":"019e0ece-41ab-74ba-b577-6e0aff6ee57c","probe":"What labeled structure appears between the Rough ER and the Nucleus?","golden":"Golgi apparatus","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** Golgi apparatus  \n**"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"}]},{"eval_id":"019e0ece-aeb7-7000-b806-b1e7d144e6f6","probe":"What color is used to depict the Golgi apparatus in this figure?","golden":"orange","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"}]},{"eval_id":"019e0ed6-4075-7e2a-8d36-a54c01ef1f0a","probe":"According to the labels in the figure, which Roman numeral is assigned to the Olfactory nerve?","golden":"I","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"}]},{"eval_id":"019e0ed6-d0db-7047-a35c-28a5f0394d4e","probe":"How many cranial nerves are labeled in this figure?","golden":"12","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"}]},{"eval_id":"019e0ed7-29c1-7353-a0d0-78dc86f5bf0d","probe":"Which cranial nerve is labeled with the Roman numeral X?","golden":"Vagus nerve","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve  \n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"vagus nerve"}]},{"eval_id":"019e0ed7-a580-70c5-9af2-82e1e6d3b27c","probe":"Which cranial nerve is labeled directly above the Trochlear nerve on the left side of the figure?","golden":"Oculomotor nerve","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III**  \n**"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III"}]},{"eval_id":"019e0ed8-e384-740f-8339-b731e7477bd0","probe":"Which Roman numeral is assigned to the Trigeminal nerve?","golden":"V","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"}]},{"eval_id":"019e0ee0-04e8-7f4f-a3d3-f732f8ce4367","probe":"What does the x-axis represent?","golden":"Time","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"}]},{"eval_id":"019e0ee2-00eb-788b-982a-17e9bbe92888","probe":"How many separate cross-section illustrations are shown in Figure 14.1.1","golden":"3","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3**  \n**"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"}]},{"eval_id":"019e0ee4-1b7c-773f-963c-fc9c8846cdc2","probe":"In the rightmost (third) illustration of Figure 14.1.1, what label appears at the far right?","golden":"Ectoderm","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"}]},{"eval_id":"019e0ee5-7413-77ac-928e-9349a0add2e3","probe":"In the far-left illustration of Figure 14.1.1, what word is labeled at the end of the curved arrow?","golden":"Convergence","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence**  \n**"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"}]},{"eval_id":"019e0ee7-d44b-7f7f-9dde-44db50c5a6d7","probe":"In panel (a), what label is shown at the top-left of the panel?","golden":"Resting muscle","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"}]},{"eval_id":"019e0ee8-0c80-7766-bb63-e01a6477af62","probe":"In panel (a), what label is shown at the top-right of the panel?","golden":"Active muscle","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"}]},{"eval_id":"019e0ee8-b795-7df0-985e-b6a23bc84e11","probe":"In panel (b), what process is shown at the top-right when oxygen is present?","golden":"Aerobic respiration","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration**  \n**"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"aerobic respiration"}]},{"eval_id":"019e0ee9-027b-7c34-9c19-e3a9f92ddc36","probe":"In panel (b), what is produced when there is no oxygen?","golden":"Lactic acid","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid (to blood)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid (lactate)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid (to blood)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid (to blood)\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid (to blood)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid (to blood)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid (to blood)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid (to blood)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid (to blood)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid (to blood)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid (to blood)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"}]},{"eval_id":"019e0ee9-9d8a-74f4-a4d4-fdae97459d0d","probe":"In panel (c), what three substances flow INTO the cellular respiration mitochondria?","golden":"Blood glucose, Pyruvic acid, Fatty acids","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids**  \n**"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids  \n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blood glucose, pyruvic acid, fatty acids"}]},{"eval_id":"019e0eee-1192-75e7-bc00-9eba77492379","probe":"In Figure 17.5.2, what does step 1 say?","golden":"Blood calcium concentration drops","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"}]},{"eval_id":"019e0eee-6b0f-7623-9bf9-f65dcda769bd","probe":"In Figure 17.5.2, what does step 4 say?","golden":"Blood calcium levels increase","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"}]},{"eval_id":"019e0ef1-0b05-7277-bad0-8b16372f30ef","probe":"In Figure 17.5.2, what is the title of item 3b?","golden":"Effects of PTH on kidneys","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"}]}]},{"summary":{"model":"gemini_3_1_pro","name":"Gemini 3.1 Pro","total_evals":550,"total_cells":2750,"l2_cells":2358,"l3_cells":276,"l4_cells":116,"acceptable":95.78,"runs":5,"partial":true,"l2_evals":459,"l3_evals":65,"l4_evals":26},"evals":[{"eval_id":"019dfaf8-7549-77d5-b050-b8468d035af7","probe":"What was the total amount of Class C share repurchases for the three months ended March 31, 2025?","golden":"$12,535 million","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"12,535\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"12,535\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"12,535\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"12,535\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"12,535\n"}]},{"eval_id":"019dfafb-3912-792d-bc47-54ca00054b5c","probe":"What were the revenues for 2025?","golden":"$402,836 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$ 402,836\n"}]},{"eval_id":"019dfafb-834e-72a8-893b-436ffbf094a2","probe":"What was the net income for 2024?","golden":"$100,118 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"100,118\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"100,118\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"100,118\n"}]},{"eval_id":"019dfafb-dcbb-70a3-96b4-fcb14e3ee61c","probe":"What was the cost of revenues for 2023?","golden":"$133,332 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"133,332\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"133,332\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"133,332\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"133,332\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"133,332\n"}]},{"eval_id":"019dfafc-94fe-761b-9254-9f753ab96d14","probe":"What was the total amount of share repurchases for the nine months ended September 30, 2025?","golden":"$40,117 million","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"40,117\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$40,117\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$40,117\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$40,117\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$40,117\n"}]},{"eval_id":"019dfb0e-3ccc-74fa-9d0d-91c2663bea11","probe":"What was the total revenue for the three months ended March 31, 2025?","golden":"$90,234 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$90,234\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$90,234\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$90,234\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"90,234\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$90,234\n"}]},{"eval_id":"019dfb0e-aa32-78f0-b197-81311a562d15","probe":"What were the total long-lived assets in the United States as of March 31, 2025?","golden":"$149,304 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"149,304\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"149,304\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"149,304\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"149,304\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"149,304\n"}]},{"eval_id":"019dfb0f-11dc-7143-87ab-1b18f0a0c5b8","probe":"What was Google Cloud's operating income for the three months ended March 31, 2025?","golden":"$2,177 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"2,177\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"2,177\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"2,177\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"2,177\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"2,177\n"}]},{"eval_id":"019dfb10-1fb2-7986-b06c-55501bbd796e","probe":"What was the United States revenue for the three months ended September 30, 2025?","golden":"$48,758 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"48,758\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"48,758\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"48,758\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758\n"}]},{"eval_id":"019dfb10-c712-7d30-9f15-c857b9160151","probe":"What was the EMEA revenue for the nine months ended September 30, 2025?","golden":"$84,096 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"84,096\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"84,096\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"84,096\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"84,096\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"84,096\n"}]},{"eval_id":"019dfb11-2196-7673-aeb2-eebcf53e53b2","probe":"What was the APAC revenue for the three months ended September 30, 2024?","golden":"$14,547 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"14,547\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"14,547\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"14,547\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"14,547\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"14,547\n"}]},{"eval_id":"019dfb20-e27a-7c39-b2f6-4f9d7929ea4e","probe":"What is the estimated fair value of total fixed maturity securities AFS as of December 31, 2022?","golden":"$276,780 million","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"276,780\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"276,780\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"276,780\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"276,780\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"276,780\n"}]},{"eval_id":"019dfb22-9390-7dca-91a4-198eb5ec30b4","probe":"What is the amortized cost net of ACL for Baa rated securities as of December 31, 2022?","golden":"$81,280 million","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"81,280\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"81,280\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"81,280\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"81,280\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"81,280\n"}]},{"eval_id":"019dfb23-4f44-7d83-91d3-79100e6cffec","probe":"What were the adjusted earnings available to common shareholders for the U.S. segment?","golden":"$2,996 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$2,996\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$2,996\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$2,996\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$2,996\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$2,996\n"}]},{"eval_id":"019dfb25-429c-7aee-a55e-43ed0574b742","probe":"What is the estimated fair value of policyholder account balances?","golden":"$115,408 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"115,408\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"115,408\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"115,408\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$115,408\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$115,408\n"}]},{"eval_id":"019dfb25-8392-72a3-af31-c1805d75def2","probe":"What is the estimated fair value of equity securities?","golden":"$1,684 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"1,684\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"1,684\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"1,684\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"1,684\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"1,684\n"}]},{"eval_id":"019dfb26-154c-7462-80c9-ac925ac520e6","probe":"What is the notional amount of foreign currency swaps?","golden":"$56,025 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"56,025\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"56,025\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"56,025\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"56,025\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"56,025\n"}]},{"eval_id":"019e000b-683c-7e54-aaf2-3d634ac03517","probe":"What is the total expenses for Education in Graph MDA-5?","golden":"$46,073 million","png_sha":"3f8e2c78a2134ddb79f740cc731c989a29e5b11d89cdb0254e1f1740d44cfdb0","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$ 46,073\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$ 46,073\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$ 46,073\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$ 46,073\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$ 46,073\n"}]},{"eval_id":"019e007d-e19f-7d15-815d-b4e94383d99b","probe":"What are the total expenses for Health and Human Services?","golden":"$75,194 million","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$ 75,194\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$ 75,194\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$ 75,194\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$ 75,194\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$ 75,194\n"}]},{"eval_id":"019e007e-5b89-72a2-b531-375ac7e4ca75","probe":"What is the dollar amount of Operating Grants and Contributions?","golden":"$74.9 billion","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9\n"}]},{"eval_id":"019e0ed1-c40b-7515-aa9e-86ffff7a7b0a","probe":"In figure (a), labeled \"Loosely held,\" what object is being held?","golden":"a pencil","png_sha":"294a4958d5ff0d4328b9ea9e75f13bb4f7ef1d09ee59316db09945f970fa281f","worst":4,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n"},{"run_index":1,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found\n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n"},{"run_index":3,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found\n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"pencil\n"}]},{"eval_id":"019dfb11-8ce1-72d9-b0ab-fc0be563e187","probe":"What were the total revenues for the nine months ended September 30, 2025?","golden":"$289,007 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$289,007\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$289,007 million\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$289,007\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"289,007\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$289,007\n"}]},{"eval_id":"019dfb23-d976-764b-875f-1c7d8d24b80e","probe":"What were the adjusted earnings for the Asia segment?","golden":"$1,378 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$1,378\n"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$1,378\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$1,378\n"}]},{"eval_id":"019dfb24-353e-721c-af95-7c83f5c7c811","probe":"What were the adjusted earnings for the EMEA segment?","golden":"$246 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$246\n"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$246\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million\n"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$246\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$246\n"}]},{"eval_id":"019dfb45-009b-71c5-a560-66fa6f28c0b7","probe":"What were the personal income taxes for 2024?","golden":"$116.5 billion","png_sha":"be9e4b96b82c2251ae314ddc72ad643547069399fbff67cb23663b4b60410b07","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"116.5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion\n"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"116.5\n"}]},{"eval_id":"019e055d-286a-7563-a7e4-fcf6471dab8b","probe":"What is the dose of infliximab listed for intensification therapy?","golden":"5\u201310 mg/kg IV for 1 dose","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"5\u201310 mg/kg\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose\n"}]},{"eval_id":"019de200-d496-74b2-a2cc-5c7a6982836d","probe":"What is the Tenant Notice Address suite number?","golden":"Suite 900","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900\n"}]},{"eval_id":"019de200-d49f-72ce-9b9d-97ba16d5640c","probe":"What is the depreciation period (useful life in years) listed in the rightmost column for every property on this page?","golden":"40 years","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"40\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"40\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"40\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"40\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"40\n"}]},{"eval_id":"019de200-d4ba-7ebb-acf4-de78451b07c1","probe":"How many miles is mentioned for relocation of the Executive's principal place of employment?","golden":"25 miles","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25)\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"25\n"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25)\n"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25)\n"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25)\n"}]},{"eval_id":"019de200-d4c1-76bf-b140-f4b73e70f7ed","probe":"What is the maximum sound level (in dBA) allowed for vacuum cleaners?","golden":"70dBA","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"70\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"70\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"70\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"70\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"70\n"}]},{"eval_id":"019de200-d4f0-7baf-9b58-1e08027b6f0d","probe":"How many RSF is the 2nd Floor Premises calculated as for Base Rent purposes?","golden":"12,000 RSF","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"12,000\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"12,000\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"12,000\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"12,000\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"12,000\n"}]},{"eval_id":"019de200-d4f1-7b08-800d-39648227b1fc","probe":"How many days advance notice must Tenant give for an Acceleration Notice?","golden":"120 days","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120\n"}]},{"eval_id":"019de200-d505-7a87-bf67-4ac7fc6b2fd3","probe":"How many days before policy expiration must original copies of policies be delivered to Landlord?","golden":"fifteen (15) days","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen (15)\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"}]},{"eval_id":"019de200-d507-733d-8d8c-87040ba6130c","probe":"How many days does Landlord have to give Tenant a termination notice after submission of the statement?","golden":"30 days","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"30\n"},{"run_index":1,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days\n"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30)\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"30\n"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30)\n"}]},{"eval_id":"019de200-d508-7af1-93e1-8436c404657e","probe":"How many business days in advance must Tenant provide the Notice of Permitted Transfer?","golden":"10 Business Days","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10\n"}]},{"eval_id":"019de200-d50e-7050-b563-d96d07356800","probe":"How many times per day must the exterior of the building be inspected and maintained?","golden":"four times per day","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four\n"}]},{"eval_id":"019de200-d515-7626-bd30-2e0c3b0c3b7f","probe":"Within how many Business Days must Borrower pay any excess if it results from a reserve against the Borrowing Base?","golden":"five (5) Business Days","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)\n"}]},{"eval_id":"019de200-d523-7d03-9cf0-aa0eb615e454","probe":"Within how many calendar days following lease termination must Lessor conduct and deliver the Phase I environmental assessment under section 11.4?","golden":"fifteen (15) calendar days","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"15\n"}]},{"eval_id":"019de200-d525-7710-85f5-fc41b54afbb0","probe":"Within how many calendar days must Lessee deliver a signed counterpart of the sublease agreement to Lessor after its execution?","golden":"five (5) calendar days","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"}]},{"eval_id":"019dfaef-4f26-7d15-9caf-4928cafc4f5e","probe":"What is the exhibit number shown at the top right of this page?","golden":"Exhibit 23.1","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1\n"}]},{"eval_id":"019dfb3f-d06a-7547-a4b6-8a6e4c150c61","probe":"What is the suite number of the office address listed at the bottom of the letter?","golden":"Suite 1850","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850\n"}]},{"eval_id":"019e0005-d4aa-7f1f-8391-f99f6caf3697","probe":"How many City Council Members are from Brooklyn?","golden":"16 Members","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"16\n"}]},{"eval_id":"019e0006-0655-7fe4-88c4-d697fbcb759a","probe":"How many Council Members does Queens have?","golden":"14 Members","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14\n"}]},{"eval_id":"019e0081-be2e-71be-9017-964db6e9e08a","probe":"What is the maximum value shown on the map's mile scale bar?","golden":"45 Miles","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"45\n"}]},{"eval_id":"019e0085-cd0d-7043-93eb-a33714bb645a","probe":"What GASB Statement number did the Council adopt in fiscal year 2024?","golden":"No. 96","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96\n"}]},{"eval_id":"019e00a4-d8d8-7d76-84d9-c255fd95f7cd","probe":"How many minutes is Mrs. Trahan recognized for?","golden":"5 minutes","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"}]},{"eval_id":"019e00a7-39d7-723b-9490-eca9ac160ad7","probe":"What time did the House reconvene after recess?","golden":"1:30 p.m.","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m.\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m.\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m.\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m.\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m.\n"}]},{"eval_id":"019e00ad-aa7b-733c-8e2b-33b7f30d7cfc","probe":"Did Senator Whittaker appear on this vote?","golden":"No, Whittaker is not listed on this page","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found\n"}]},{"eval_id":"019e00af-5886-7c0c-acb0-3467635835d6","probe":"What time did the recorded vote take place (the \u25a1 time stamp before the McGOVERN demand)?","golden":"1:56 PM (1356)","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"1356\n"}]},{"eval_id":"019e00af-a493-76fe-9fc1-0e6baa42ab53","probe":"What time did the House return from recess (the \u25a1 time stamp before \"AFTER RECESS\")?","golden":"1:30 PM (1330)","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"1330\n"}]},{"eval_id":"019e00b0-60e7-7eb0-ace3-4de6646279c2","probe":"Which members changed their vote from \"yea\" to \"nay\"?","golden":"Ms. Ross, Mrs. Foushee, Mr. Raskin, and Mr. Krishnamoorthi","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi\n"},{"run_index":1,"verdict":3,"source":"human","note":"title/honorific handling","answer":"ROSS, FOUSHEE, RASKIN, and KRISHNAMOORTHI\n"},{"run_index":2,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI\n"},{"run_index":3,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi\n"},{"run_index":4,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ross, Foushee, Raskin, and Krishnamoorthi\n"}]},{"eval_id":"019e00b5-3554-76cc-805e-ff8228bfefae","probe":"What was the rollcall vote number for the vote on Amendment No. 8?","golden":"Rollcall Vote No. 6 Leg.","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"6\n"}]},{"eval_id":"019e00b6-0ba2-731c-a9ed-436b1a7ef320","probe":"What was the rollcall vote number for the vote on S. 5?","golden":"Rollcall Vote No. 7 Leg.","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7\n"}]},{"eval_id":"019e051b-f048-7557-907e-87bf1f5319e0","probe":"What was the rollcall vote number for the Driscoll nomination?","golden":"Rollcall Vote No. 90 Ex.","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90 Ex.\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"90\n"}]},{"eval_id":"019e0520-1d4b-7483-9ed6-1c012178bbd9","probe":"How many years has Jess Andrews run Senator Kennedy's communications shop?","golden":"5 years","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"}]},{"eval_id":"019e054b-b654-74aa-b2b0-ad19e229a916","probe":"What is the preferred alternative immunomodulator listed for hospitalized patients requiring HFNC oxygen or NIV?","golden":"IV tocilizumab (Blla)","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab\n"}]},{"eval_id":"019e05b1-edb1-71fd-a8f1-178c8ce2372a","probe":"How many hours per day of prone ventilation does the Panel recommend?","golden":"12 to 16 hours","png_sha":"f2687af1be946044a236b7f11f8cf6f728ef1c4e9e442378d2a6ad846b6a54e4","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"12 to 16\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"12 to 16\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"12 to 16\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"12 to 16\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"12 to 16\n"}]},{"eval_id":"019e05e7-ce2c-772c-8efd-a4776364273c","probe":"What is the figure number for the blood pressure image?","golden":"Figure 1.0","png_sha":"4fb66d797829b4efe7d38ed6d367871d6664885f70ef83a42d3f0dfec31552e6","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"}]},{"eval_id":"019e0a6f-0c3e-7520-884b-307d309c1b4b","probe":"What percentage of the human body is oxygen?","golden":"65.0%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0\n"}]},{"eval_id":"019e0a70-8117-7662-8777-c2511bc6f2ee","probe":"What percentage of the human body is phosphorus?","golden":"1.0%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0\n"}]},{"eval_id":"019e0a71-574c-7f62-97db-97525ad2820e","probe":"What is the figure number for the two models of atomic structure?","golden":"Figure 2.1.2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"2.1.2\n"}]},{"eval_id":"019e0a76-b33e-7648-8be4-ced32e601bf5","probe":"What element is shown in the planetary model?","golden":"Helium (He)","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"helium\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"helium\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"helium\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"helium\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"helium\n"}]},{"eval_id":"019e0a77-09dc-7990-a971-9e556b040d8c","probe":"What symbol is used to label the electron in the planetary model?","golden":"e\u2212","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b\n"}]},{"eval_id":"019e0a82-da2f-727f-896b-27e752c2b42b","probe":"What are the two types of fatty acids labeled in the phospholipid diagram?","golden":"Saturated fatty acid and unsaturated fatty acid","png_sha":"a2c418cbcdc6704d925ad4ffdd78dee38a58fc1ea68774d0094b65c486a66bf8","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and unsaturated\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"saturated and unsaturated\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and unsaturated\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and unsaturated\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and unsaturated\n"}]},{"eval_id":"019e0a9d-62f1-726d-9b24-bbeb2b85b199","probe":"According to the caption of Figure 3.1.5, which side of the membrane (left or right) shows the hypertonic solution?","golden":"the right side","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"right\n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"right\n"}]},{"eval_id":"019e0ad4-4005-7307-aae9-78e3049f1a65","probe":"What are the three lines that pluripotent embryonic stem cells differentiate into?","golden":"Endoderm, Mesoderm, and Ectoderm","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line\n"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line\n"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line\n"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line\n"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line\n"}]},{"eval_id":"019e0ed2-1e72-7fe1-94ee-e4dcffb88ace","probe":"In figure (a), what body part is gripping the pencil?","golden":"a hand","png_sha":"294a4958d5ff0d4328b9ea9e75f13bb4f7ef1d09ee59316db09945f970fa281f","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"Hand\n"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"Hand\n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"Hand\n"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"Hand\n"},{"run_index":4,"verdict":3,"source":"human","note":"article handling","answer":"hand\n"}]},{"eval_id":"019e0ede-f3cd-7412-8c25-2e079510e6e7","probe":"What is the unit shown on the y-axis label?","golden":"mV (millivolts)","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"mV\n"}]},{"eval_id":"019e0edf-b3c8-7227-995d-59d8e7337a13","probe":"What is the membrane potential value at the dashed horizontal line labeled \"Threshold\"?","golden":"-55 mV","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"-55\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"-55\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"-55\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"-55\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"-55\n"}]},{"eval_id":"019e0eea-1322-709e-b1c1-430100607e7d","probe":"In panel (c), what four products come OUT of cellular respiration?","golden":"ATP, Heat, CO\u2082, H\u2082O","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O\n"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O\n"}]},{"eval_id":"019e0eea-ac39-7b97-941e-8c1e0a744ae3","probe":"In panel (c), what additional input enters the mitochondria from above (with a downward arrow)?","golden":"O\u2082 (oxygen)","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"O2\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"O2\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"O2\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"O2\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"O2\n"}]},{"eval_id":"019de200-d4bb-7ca6-ada6-5158e0ca9947","probe":"What is the item number for the Foreperson/Day Porter Executive dress shirt?","golden":"#828","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"828\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828\n"}]},{"eval_id":"019de200-d4c3-7771-b087-cb7f248214a4","probe":"What is the item number listed for the women's Long Sleeve Dress Blouse?","golden":"#528","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"528\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\n"}]},{"eval_id":"019de200-d4ec-7fff-aceb-46c812561273","probe":"Which floors of the Building are designated as the Must Take Expansion Premises?","golden":"Floors 5, 6 and 7","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"floors 5, 6 and 7\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7\n"}]},{"eval_id":"019de200-d514-76a5-be6d-0713d4261c08","probe":"What is the full deadline (both time of day and number of business days) by which a Notice of Borrowing must be delivered before a proposed borrowing?","golden":"1:00 p.m. (Eastern time) two (2) Business Days prior","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days\n"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"before 1:00 p.m. (Eastern time) two (2) Business Days prior\n"}]},{"eval_id":"019de200-d518-778a-9421-02c7d2e3a05a","probe":"What is the section number for 'Time is of the Essence'?","golden":"Section 1.4","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4\n"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4\n"}]},{"eval_id":"019de740-e7d8-75d0-835d-3a79745c66cc","probe":"How many consecutive Business Days after Landlord's receipt of the Untenantability Notice are required (in non-Force Majeure cases)?","golden":"five (5)","png_sha":"658d8ecfa29b1c0cf9870b2d1c622a5cff7347859e7674b418cc4660be4eb7b9","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5)\n"}]},{"eval_id":"019dfb22-1d21-7795-bb3e-bdc661245cb9","probe":"What is the % of Total for Aaa/Aa/A rated securities as of December 31, 2021?","golden":"70.4%","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"70.4\n"}]},{"eval_id":"019dfffd-a1d4-7a49-94b8-3ef9aa5497d4","probe":"What are the two highest courts shown under the Judicial branch?","golden":"The Supreme Court of Texas and The Court of Criminal Appeals","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals\n"},{"run_index":2,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"The Supreme Court of Texas, The Court of Criminal Appeals\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals\n"}]},{"eval_id":"019dffff-131f-7d34-8e0c-2be25da41c0d","probe":"What two courts are shown at the bottom level under County-Level Courts?","golden":"Municipal Courts and Justice of the Peace Courts","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*\n"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts\n"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Municipal Courts* and Justice of the Peace Courts*\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts\n"}]},{"eval_id":"019e0009-af38-766a-9ac7-cb0908ad2999","probe":"What percent of the assets of the Colleges and Universities does the University of Texas System constitute?","golden":"72.9 percent","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"72.9\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent\n"}]},{"eval_id":"019e000a-7052-7138-b0db-733f874d02cd","probe":"What percent of the expenditures for the State Highway Fund does the Texas Department of Transportation constitute?","golden":"99.9 percent","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"99.9%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"99.9%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent\n"}]},{"eval_id":"019e002a-8546-75d0-9290-e4f34687786f","probe":"What year ended is referenced at the top of the page?","golden":"December 31, 2024","png_sha":"4ceaa28bf7551920a1890b7fbf19a27b1cc875ad22828548d20d5021ffb4cb9e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"2024\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"2024\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"2024\n"}]},{"eval_id":"019e003d-d1bc-7fb0-a78b-4b79600f8252","probe":"Who is the Custodian of Funds?","golden":"Brad Lander, Comptroller of the City of New York","png_sha":"89c77daf9c6f881f0116f445cbf736cffc12698b60a93b437699a1a075b00138","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brad Lander, Comptroller of the City of New York\n"},{"run_index":2,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander\n"},{"run_index":3,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander\n"},{"run_index":4,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander\n"}]},{"eval_id":"019e051f-e004-7dd8-b253-949abd5846ae","probe":"Who is Jess Andrews leaving to work for, according to Senator Kennedy's tribute?","golden":"the new Senator from Ohio","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"article handling","answer":"our new Senator from Ohio\n"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"our new Senator from Ohio\n"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"our new Senator from Ohio\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the new Senator from Ohio\n"}]},{"eval_id":"019e055e-28ea-7f76-943f-b37787cd73cb","probe":"What is the IV dose range for high-dose anakinra?","golden":"5\u201310 mg/kg/day","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg/day\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day\n"}]},{"eval_id":"019e05ac-b930-79c4-93f6-be96e504477e","probe":"Within how many months of a recent SARS-CoV-2 infection may substantial immunity be conferred, according to footnote b?","golden":"3-6 months","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"3-6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136\n"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"3-6\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"3-6\n"}]},{"eval_id":"019e05f9-174d-779b-8451-840365bb3ab1","probe":"What type of muscle cell is shown at the Cellular level in the pyramid?","golden":"Smooth muscle cell","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"Smooth\n"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"Smooth\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell\n"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"Smooth\n"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"Smooth\n"}]},{"eval_id":"019e0a70-2afd-7288-98b1-ce3d3fbfaa95","probe":"What percentage of the human body is calcium?","golden":"1.5%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.5%\n"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5\n"}]},{"eval_id":"019e0a9e-aa0f-7a55-89e3-a0cd7f73e21f","probe":"What chemical formula is shown next to each red blood cell in the bottom row of Figure 3.1.6?","golden":"H2O","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O\n"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O\n"}]},{"eval_id":"019e0ac6-e7e3-7800-ac52-eee064e4e8b7","probe":"What is the scale bar length shown in the microscope images?","golden":"5 \u03bcm","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm\n"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm\n"}]},{"eval_id":"019de200-d48b-7a0c-9e79-d846c27a96b5","probe":"What page does Article XI Security Deposit start on?","golden":"50","png_sha":"625ba89847b64383ae07efde4a0b7374c88fd2b6dcff552df6812dad32d03160","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50\n"}]},{"eval_id":"019de200-d48c-70ff-b28a-a9c240e3486b","probe":"Who is the landlord named on this office lease?","golden":"Lanham Office 2015 LLC","png_sha":"625ba89847b64383ae07efde4a0b7374c88fd2b6dcff552df6812dad32d03160","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC\n"}]},{"eval_id":"019de200-d48d-703c-b522-b34424519003","probe":"What is Exhibit L?","golden":"Competitor List","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List\n"}]},{"eval_id":"019de200-d48e-767a-b928-9b2d12086653","probe":"What is Exhibit H?","golden":"Roof Access Agreement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement\n"}]},{"eval_id":"019de200-d48f-7596-abf5-cacd23054c4d","probe":"What is Exhibit J?","golden":"Parking Easement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement\n"}]},{"eval_id":"019de200-d490-71ff-a39d-ee962a11796e","probe":"What is Exhibit D?","golden":"Certificate Affirming the Must Take Commencement Date","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date\n"}]},{"eval_id":"019de200-d491-71d6-875d-4fa564623978","probe":"What is Exhibit B?","golden":"Work Agreement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement\n"}]},{"eval_id":"019de200-d492-726b-87fc-5718790d5ebd","probe":"What is Exhibit E?","golden":"Measurement Schedule","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule\n"}]},{"eval_id":"019de200-d493-74c3-af46-0469929cc88d","probe":"What is the Tenant Notice Address?","golden":"8201 Corporate Drive, Suite 900, Landover, MD 20785","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer, until Tenant has commenced full business operations at the Premises, and thereafter, the Premises, Attention: Chief Financial Officer, after Tenant has commenced full business operations at the Premises. With a copy to: General Counsel.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer, until Tenant has commenced full business operations at the Premises, and thereafter, the Premises, Attention: Chief Financial Officer\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer, until Tenant has commenced full business operations at the Premises, and thereafter, the Premises, Attention: Chief Financial Officer, after Tenant has commenced full business operations at the Premises. With a copy to: General Counsel.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8201 Corporate Drive, Suite 900, Landover, MD 20785, and thereafter, the Premises\n"}]},{"eval_id":"019de200-d494-73d8-930e-be33d26373fa","probe":"What section is referenced for the definition of 'Tax Benefits'?","golden":"Section 5.6","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6\n"}]},{"eval_id":"019de200-d495-7bf0-9c87-96d57c098e71","probe":"What section is referenced for the definition of 'Threshold Successors'?","golden":"Section 10.1","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1\n"}]},{"eval_id":"019de200-d497-758c-9ad2-fceee7efd1fa","probe":"What section is referenced for the definition of 'Tenant's Plans'?","golden":"Section 9.4(a)","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)\n"}]},{"eval_id":"019de200-d498-741d-b3e0-3374c9b02dfc","probe":"What is the title of section H?","golden":"Tenant Modular Furniture","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE\n"}]},{"eval_id":"019de200-d499-74c0-a9b3-74b464fcf74b","probe":"What is the color name listed for the carpet base?","golden":"503 Ginger","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger\n"}]},{"eval_id":"019de200-d49a-7b22-8b95-3fe120b21efc","probe":"What is the section number for the CARPET section?","golden":"09680","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680\n"}]},{"eval_id":"019de200-d49b-76ae-aecb-69e6ba967a73","probe":"What is the section number for the PAINTING section?","golden":"09900","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900\n"}]},{"eval_id":"019de200-d49c-75ca-963f-0649d0c70719","probe":"What is the section number for ACOUSTICAL CEILING?","golden":"09510","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510\n"}]},{"eval_id":"019de200-d49d-7cee-91a2-4ed07626e90a","probe":"What is the name of the company shown in the schedule heading on this page?","golden":"Acadia Realty Trust","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST\n"}]},{"eval_id":"019de200-d49e-7120-8c57-be2e37f1a894","probe":"What is the page number shown at the bottom of the upper section of this page?","golden":"166","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166\n"}]},{"eval_id":"019de200-d4a0-7403-856e-aa22d2bdae81","probe":"What is the name of the company shown at the top of the page?","golden":"Acceleron Pharma Inc.","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc.\n"}]},{"eval_id":"019de200-d4a1-7f82-aa55-38eac3b9b487","probe":"What is the total deferred tax assets for 2017 (in thousands)?","golden":"145,657","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657\n"}]},{"eval_id":"019de200-d4a2-7a39-91ad-766fdf7c2010","probe":"What is the page number shown at the bottom center of the page?","golden":"F-29","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29\n"}]},{"eval_id":"019de200-d4a3-7518-9715-cc1bb9edb084","probe":"What is the deferred revenue amount for 2016 (in thousands)?","golden":"1,666","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666\n"}]},{"eval_id":"019de200-d4a4-7cca-a0e9-a3ce81d8b684","probe":"What is the federal income tax expense at the statutory rate for 2015?","golden":"34.0%","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0 %\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0 %\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0 %\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0 %\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0 %\n"}]},{"eval_id":"019de200-d4a5-753e-87a5-2c51cb711be4","probe":"What is the Research and development credits amount for 2017 (in thousands)?","golden":"12,548","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548\n"}]},{"eval_id":"019de200-d4a6-72d4-b715-3cd7f42e4f66","probe":"What is the State income tax, net of federal benefit percentage for 2016?","golden":"5.9%","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9 %\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9 %\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9 %\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9 %\n"}]},{"eval_id":"019de200-d4a7-74af-afa8-d3ad189499cc","probe":"What is the deposit amount mentioned in this document?","golden":"$500,000.00","png_sha":"5a5e3841491b2b356eb9b963e45419183ebf6ffae298e69a6f9dd5488bc23e1c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"}]},{"eval_id":"019de200-d4a8-7bdc-bc00-d50a60d60dcc","probe":"What is the title of section 16?","golden":"Mutual Waiver of Subrogation Rights","png_sha":"674a83793665d045c76513a816f7fc9099c52baccd94af7ee817a5f89cdc81d5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights.\n"}]},{"eval_id":"019de200-d4a9-7107-917d-4d1e160c26b3","probe":"What is the anticipated commencement date?","golden":"March 1, 2016","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016\n"}]},{"eval_id":"019de200-d4aa-7225-85f5-76e6b1382af9","probe":"What is the premises address?","golden":"2665 North First Street, Suite 300, San Jose, California 95134","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134\n"}]},{"eval_id":"019de200-d4ab-727c-ae0c-07bdc5f94836","probe":"What is the tenant's trade name?","golden":"8x8, Inc.","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc.\n"}]},{"eval_id":"019de200-d4ac-742d-b65a-74bd92f2893d","probe":"What is the name of the broker listed in Section 31?","golden":"Cresa Global, Inc.","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc.\n"}]},{"eval_id":"019de200-d4ad-71b2-aae9-616c2d5fdb91","probe":"What is the title of Section 33?","golden":"Holding Over","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over\n"}]},{"eval_id":"019de200-d4ae-7bb5-8e56-dfba0d289a6a","probe":"What is the title of Section 38?","golden":"Miscellaneous","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous\n"}]},{"eval_id":"019de200-d4af-7ae9-9bf2-f9ad2d8f5ea5","probe":"What is the title of Section 32?","golden":"Estoppel Certificate","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate\n"}]},{"eval_id":"019de200-d4b0-7068-9693-c265751b0823","probe":"What is the title of Section 34?","golden":"Assignment and Subletting","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting\n"}]},{"eval_id":"019de200-d4b1-72c3-a2c1-2ee5369782dd","probe":"What is the title of Section 31?","golden":"Broker's Commissions","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions\n"}]},{"eval_id":"019de200-d4b2-7946-80ee-a29424252d23","probe":"What is the title of section 14.3?","golden":"Transfer Premium","png_sha":"cde4659cf5512e2c7b127af66eb4bab815dcc533bb04fce540d6d56b21cbb6cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium\n"}]},{"eval_id":"019de200-d4b3-7330-8b3a-3010528a30fa","probe":"What is the title of section 14.5?","golden":"Effect of Transfer","png_sha":"cde4659cf5512e2c7b127af66eb4bab815dcc533bb04fce540d6d56b21cbb6cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer\n"}]},{"eval_id":"019de200-d4b4-702e-932f-bb5b6dbb2b20","probe":"What is the title of Article XXIX?","golden":"Expansion Rights","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS\n"}]},{"eval_id":"019de200-d4b5-709e-9897-f8440e2a964f","probe":"What is the title of Article XXX?","golden":"METROPLEX II ASSUMPTION","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX II ASSUMPTION\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metroplex II Assumption\n"}]},{"eval_id":"019de200-d4b6-73e9-aa56-a2eb7119541a","probe":"What is the title of Section 29.1?","golden":"Right of First Refusal","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal\n"}]},{"eval_id":"019de200-d4b7-7604-b550-db1d11ebef12","probe":"What is the title of Section 28.2?","golden":"Additional Amenities","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities\n"}]},{"eval_id":"019de200-d4b8-7164-91b2-3ec03d9f397f","probe":"What is the title of section 12?","golden":"Severance Payments","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments\n"}]},{"eval_id":"019de200-d4b9-723f-8a38-4f373e93bffa","probe":"What is the title of section 13?","golden":"Certain Covenants of the Executive","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive\n"}]},{"eval_id":"019de200-d4bc-76fc-9589-06797f38e895","probe":"What is the title of section E?","golden":"UNIFORMS","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS\n"}]},{"eval_id":"019de200-d4bd-7e20-a10a-47c622032b52","probe":"What is the item number for the women's Pleated Dress Pants?","golden":"#596","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596\n"}]},{"eval_id":"019de200-d4be-7e4d-b5ce-bf5d0d9e3745","probe":"What is the title of section J?","golden":"LIGHTING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING\n"}]},{"eval_id":"019de200-d4bf-7a42-91f9-d00fe759f635","probe":"What is the title of section H?","golden":"SECURITY AND INCIDENT REPORTING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING\n"}]},{"eval_id":"019de200-d4c0-7843-8047-cc09e991e12b","probe":"What is the title of section K?","golden":"GREEN CLEANING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING\n"}]},{"eval_id":"019de200-d4c2-7ad3-88a8-ed0b24b345b7","probe":"What is the item number for the men's Foreperson/Day Porter Pleated dress pants?","golden":"#865","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865\n"}]},{"eval_id":"019de200-d4c4-736b-b432-833199724c46","probe":"What is the title of section 24.0?","golden":"HOLDOVER","png_sha":"214b816ecbf747322726d54a0cb92edd6d184be6a6e04656e532d637c65eda11","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER\n"}]},{"eval_id":"019de200-d4c5-7b98-9a5a-c76d5fb5ae1e","probe":"What is the title of section 5.2?","golden":"Operating Expenses; Consumable Expenses and Base Building Expenses","png_sha":"3343506981bd41f08b63b8df40f8ba763e2bc1566a850d0903f24b1c5782cf77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses.\n"}]},{"eval_id":"019de200-d4c6-7729-866a-8ac3402457fb","probe":"What is the title of Article XIV?","golden":"Assignment and Subletting","png_sha":"d8fa233fb12db1beef1e4088d39215700d5884c2d4cb968b6985c6febde8a2ca","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING\n"}]},{"eval_id":"019de200-d4c7-7305-82b7-76d4d75e7f9d","probe":"What is the title of Article XIII?","golden":"Condemnation","png_sha":"d8fa233fb12db1beef1e4088d39215700d5884c2d4cb968b6985c6febde8a2ca","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION\n"}]},{"eval_id":"019de200-d4c8-787c-9ed4-e33640efb435","probe":"What is the title of Article 28?","golden":"Confidentiality","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Confidentiality\n"}]},{"eval_id":"019de200-d4c9-7b7f-9e32-c47d4f1c0b0e","probe":"What is the title of Exhibit D?","golden":"Form of Deed","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed\n"}]},{"eval_id":"019de200-d4ca-7805-9cc9-6e26cd367bbc","probe":"What is the title of Article 25?","golden":"Waiver of Jury Trial","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial\n"}]},{"eval_id":"019de200-d4cb-70dc-a225-ac7807b5a70c","probe":"What is the title of Article 33?","golden":"Costs and Attorneys' Fees","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees\n"}]},{"eval_id":"019de200-d4cc-7013-9323-c4a463e49255","probe":"What is the Lessor's telephone number listed in the notices section?","golden":"(81) 8358.7978","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"}]},{"eval_id":"019de200-d4cd-7c1a-a4b1-fd5dc2875413","probe":"What is the title of section 24.4?","golden":"Captions","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions\n"}]},{"eval_id":"019de200-d4ce-73b9-b787-b0f7568e7018","probe":"What is the Lessee's telephone number listed in the notices section?","golden":"(81) 8158.8800","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8158.8800\n"}]},{"eval_id":"019de200-d4cf-7e95-8f4b-cca6ed5396ce","probe":"What is the title of section 24.5?","golden":"Severability","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability\n"}]},{"eval_id":"019de200-d4d0-7008-bd98-2d410f1fb7fa","probe":"What is the name of the person to contact for the Lessor in the notices section?","golden":"Mr. Juan Carlos Gonzalez Quezada","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada\n"}]},{"eval_id":"019de200-d4d1-7e39-92cb-dc82b006e040","probe":"What is the title of section 24.1?","golden":"Brokers","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers.\n"}]},{"eval_id":"019de200-d4d2-7ff3-ae3f-b7ce26ebedc4","probe":"What is the title of section 22.3?","golden":"Labor","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor\n"}]},{"eval_id":"019de200-d4d3-7a72-9dfe-0011bce8efc8","probe":"What is the maximum tenant improvement allowance amount in dollars?","golden":"$559,160.00","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00\n"}]},{"eval_id":"019de200-d4d4-7185-bf69-9197f90e27ce","probe":"What is the title of Section II?","golden":"TENANT'S WORK","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK\n"}]},{"eval_id":"019de200-d4d5-7ac3-8e4e-c758cbae290a","probe":"What is the per square foot dollar amount mentioned for the Allowance?","golden":"$40.00","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40.00\n"}]},{"eval_id":"019de200-d4d6-77e1-9296-5f9e11cf7728","probe":"What does item (c) say?","golden":"Intentionally deleted.","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted.\n"}]},{"eval_id":"019de200-d4d7-71ee-b89a-13f57933c5ed","probe":"What is the company name shown in the headers of the financial statements?","golden":"Acadia Realty Trust and Subsidiaries","png_sha":"d99abf4bae64753a77c680d1e83acdbdc08eb377e9da9bc0a4af8337f67971e2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES\n"}]},{"eval_id":"019de200-d4d8-73df-b318-56c93e913a1d","probe":"What is the rent payable for December 2016 in the Metroplex Rent table?","golden":"137,399","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399\n"}]},{"eval_id":"019de200-d4d9-7080-91a1-8e4024ae5b27","probe":"What is the title of Exhibit M?","golden":"Metroplex Rent","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT\n"}]},{"eval_id":"019de200-d4da-740b-af0a-30cdbbdc3a00","probe":"What is the rent payable for July 2018?","golden":"145,763","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"}]},{"eval_id":"019de200-d4db-76f8-b9cf-eb901aaef607","probe":"What is the title of Exhibit N?","golden":"Exclusions From Operating Expenses","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses\n"}]},{"eval_id":"019de200-d4dc-76d9-b19c-2bb2f2c2d455","probe":"What is the rent payable for March 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"}]},{"eval_id":"019de200-d4dd-7a8e-97e8-6cbb97c9f288","probe":"What is the rent payable for January 2018?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"}]},{"eval_id":"019de200-d4de-7510-a1bb-a2200cf532b1","probe":"What is the rent payable for May 2018?","golden":"145,763","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763\n"}]},{"eval_id":"019de200-d4df-72db-b8e2-5470717b76c7","probe":"What is the rent payable for September 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"}]},{"eval_id":"019de200-d4e0-7497-8998-04b404a57589","probe":"What is listed as item (i) under Excluded Expenses in Exhibit N?","golden":"Real Estate Taxes","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes\n"}]},{"eval_id":"019de200-d4e1-704d-bad7-731b3da45bdf","probe":"What is the rent payable for November 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524\n"}]},{"eval_id":"019de200-d4e2-7aab-ae79-29c74e645fca","probe":"What is the title of Exhibit C?","golden":"Technology Exhibit","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT\n"}]},{"eval_id":"019de200-d4e3-7937-8135-40c4b4f0cb8e","probe":"What is the markup percentage on outgoing mail?","golden":"10%","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%\n"}]},{"eval_id":"019de200-d4e4-7765-86d5-d5fb371119ed","probe":"What is the title of Exhibit B?","golden":"Summit Billing Information","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION\n"}]},{"eval_id":"019de200-d4e5-7bb2-9e8d-5d17eac142de","probe":"What is the reconnection fee per hour mentioned in Exhibit C?","golden":"$100","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"}]},{"eval_id":"019de200-d4e6-7499-90b0-274586c057d5","probe":"What are the standard business hours listed for Summit's remedial maintenance?","golden":"9:00 am to 5:00 pm, Monday - Friday","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday\n"}]},{"eval_id":"019de200-d4e7-7aba-997b-697fce37c98b","probe":"Who signed as Chief Executive Officer of 1847 Holdings LLC?","golden":"Ellery W. Roberts","png_sha":"17421f00db7e68e09f420ba5abd403a8bc79b47f8f380327515bff5297f38fed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts\n"}]},{"eval_id":"019de200-d4e8-7f62-96ae-519b14f37f5f","probe":"On what day of December 2024 did the Guarantors execute this Guaranty?","golden":"13th","png_sha":"17421f00db7e68e09f420ba5abd403a8bc79b47f8f380327515bff5297f38fed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th\n"}]},{"eval_id":"019de200-d4e9-71c2-9557-1e2c70c1e1fb","probe":"What is the Per RSF Base Rent for the Initial Term?","golden":"$20.50","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Twenty and 50/100 Dollars ($20.50)\n"}]},{"eval_id":"019de200-d4ea-7529-926e-f6d2957fdefe","probe":"Who is the Named Tenant?","golden":"2U Harkins Road LLC","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC\n"}]},{"eval_id":"019de200-d4eb-7ccd-933d-0af15a613cf0","probe":"What is the Alteration Threshold dollar amount?","golden":"$200,000.00","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00\n"}]},{"eval_id":"019de200-d4ed-7a5a-bca1-903c35b0c671","probe":"What is the speed limit mentioned in rule 4 of the parking rules?","golden":"5 miles per hour","png_sha":"4a35d25bb27a032bf2661265ea4187cfc0129b1d6aa4a12ae16fc6380aea8e4c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour\n"}]},{"eval_id":"019de200-d4ee-76cd-96ee-560ea13db477","probe":"What are the parking hours listed in rule 1?","golden":"7:30 a.m. to 6:30 p.m., Monday through Friday","png_sha":"4a35d25bb27a032bf2661265ea4187cfc0129b1d6aa4a12ae16fc6380aea8e4c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday\n"}]},{"eval_id":"019de200-d4ef-7bf8-a7ba-27307744e3f9","probe":"What is the 2nd Floor Build-Out Allowance amount?","golden":"$600,000.00","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00\n"}]},{"eval_id":"019de200-d4f2-7a99-af6e-94a36878aec2","probe":"What is the per-RSF dollar amount used to calculate the Must Take Allowance?","golden":"$46.50","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50\n"}]},{"eval_id":"019de200-d4f3-7347-815c-24a4e9f82950","probe":"In the example, what is the Must Take Allowance for the 7th floor?","golden":"$1,198,611.65","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65\n"}]},{"eval_id":"019de200-d4f4-7dcb-9449-8179714e49d7","probe":"What is the limit of liability for Landlord's commercial general liability insurance?","golden":"$5,000,000 per occurrence","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000 per occurrence\n"}]},{"eval_id":"019de200-d4f5-78f3-8340-3580046edcc8","probe":"What is the each occurrence limit for Personal Injury Liability?","golden":"$9,000,000","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000\n"}]},{"eval_id":"019de200-d4f6-7741-884c-42611e27bcef","probe":"What is the Insured's participation percentage for Personal Injury Liability?","golden":"0%","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%\n"}]},{"eval_id":"019de200-d4f7-7940-b10a-9822b81b3272","probe":"What is the Lobby Renovations Allowance?","golden":"$500,000.00","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)\n"}]},{"eval_id":"019de200-d4f8-7a38-8a19-517016d4b55b","probe":"What is the Initial Build-Out Allowance per RSF?","golden":"$48.00","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48.00\n"}]},{"eval_id":"019de200-d4f9-7748-a94b-9e4c68688de5","probe":"What is the construction supervision fee percentage Landlord charges on hard construction costs?","golden":"1%","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%\n"}]},{"eval_id":"019de200-d4fa-70fc-b7a8-b9c26c2b14e0","probe":"By what date must Tenant substantially complete the 2nd Floor Build-Out Work?","golden":"April 1, 2018","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018\n"}]},{"eval_id":"019de200-d4fb-7f01-8927-c6d175a34ace","probe":"By what date must Tenant substantially complete the Initial Build-Out Work of the Initial Premises?","golden":"April 1, 2017","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017\n"}]},{"eval_id":"019de200-d4fc-7cca-908f-984e3d8120e7","probe":"What is the umbrella liability each occurrence amount?","golden":"$5,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000\n"}]},{"eval_id":"019de200-d4fd-74c2-abb8-1bb3a38e217c","probe":"What is the medical payments coverage amount?","golden":"$5,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 5,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 5,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 5,000\n"}]},{"eval_id":"019de200-d4fe-76cb-bdd6-bb011389179c","probe":"What is the fire damage legal liability coverage amount?","golden":"$50,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000\n"}]},{"eval_id":"019de200-d4ff-7fd5-9027-7197160465a2","probe":"What is the automobile liability combined single limit amount?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"}]},{"eval_id":"019de200-d500-7cfe-8ff2-d8bbbb64073a","probe":"What is the bodily injury by accident coverage amount per accident under Workers' Compensation Coverage B?","golden":"$500,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000\n"}]},{"eval_id":"019de200-d501-782d-845b-a4e35e143c20","probe":"What is the combined single limit per occurrence for Coverage A under Commercial General Liability?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"}]},{"eval_id":"019de200-d502-7a8b-9ba6-c9892e2eeecc","probe":"What insurance form is the general liability insurance to be written on?","golden":"2001 Insurance Services Office form","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form or its equivalent\n"}]},{"eval_id":"019de200-d503-798a-afa1-45a2677f34db","probe":"What is the personal and advertising injury liability (Coverage B) amount?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000\n"}]},{"eval_id":"019de200-d504-70ea-9d31-b199175fed3c","probe":"In what geographic area must business interruption insurance match amounts customarily carried by responsible tenants?","golden":"Greater Boston","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the Greater Boston area\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area\n"}]},{"eval_id":"019de200-d506-744e-be70-a75cf629bab5","probe":"What is the non-refundable assignment/sublease review fee?","golden":"$1,500","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500\n"}]},{"eval_id":"019de200-d509-782f-8cb5-81249701c47f","probe":"What percentage of the excess must Tenant pay to Landlord as Assignment/Sublease Excess Rent?","golden":"100%","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%\n"}]},{"eval_id":"019de200-d50a-7a93-8a69-a34202f99ee3","probe":"What is the term used for the portion of Premises eliminated under the Elimination Period?","golden":"Eliminated Space","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space\n"}]},{"eval_id":"019de200-d50b-714d-a6f0-8fbb3c33bc67","probe":"What is the term defined for the date immediately prior to the effective date of the proposed assignment?","golden":"Earlier Termination Date","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date\n"}]},{"eval_id":"019de200-d50c-743d-ad76-780e2c2fb12d","probe":"What is the term used for the period after the Elimination Period during which the Eliminated Space is restored to the Premises?","golden":"Restoration Period","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Restoration Period\"\n"}]},{"eval_id":"019de200-d50d-7c5f-a9f2-1705d2b33bc2","probe":"What is the term defined for the consideration payable by the assignee or subtenant?","golden":"Assignment/Sublease Consideration","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration\n"}]},{"eval_id":"019de200-d50f-730f-bba3-567d098ebd36","probe":"By what time each weekday must the stainless steel tops on the 18th Street light boxes be wiped down?","golden":"8:00 AM","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM\n"}]},{"eval_id":"019de200-d510-7320-b95d-f545ed219bc5","probe":"How often must window frames and ledges be swept with a soft-bristled brush on the building exterior?","golden":"Monthly","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly\n"}]},{"eval_id":"019de200-d511-7272-9565-2412f58e253c","probe":"How often must service area floors be dust mopped, at minimum?","golden":"Once per week","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"once per week\n"}]},{"eval_id":"019de200-d512-7496-808b-5b1ea05ca3f8","probe":"How often must standpipe fire hose connections on the exterior of the building be cleaned and polished?","golden":"Weekly","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"WEEKLY\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly\n"}]},{"eval_id":"019de200-d513-7149-ae8c-e8a7754d572b","probe":"What is the minimum amount for a partial prepayment of Revolving Loans?","golden":"$100,000","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000\n"}]},{"eval_id":"019de200-d516-7459-9245-cc659422a55c","probe":"By what time on the Termination Date must the entire outstanding principal of each Revolving Loan be paid?","golden":"12:00 Noon (Eastern time)","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12:00 Noon (Eastern time)\n"}]},{"eval_id":"019de200-d517-7577-ad4f-c469f0a5f3e3","probe":"What is the higher integral multiple required for partial prepayments of Revolving Loans?","golden":"$25,000","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000\n"}]},{"eval_id":"019de200-d519-76a9-b52e-17fb3cd3da08","probe":"What rate do Revolving Loans accrue interest at, plus the Applicable Margin?","golden":"LIBOR Rate","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the LIBOR Rate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate\n"}]},{"eval_id":"019de200-d51a-7cbd-841b-aa945ef2b4a8","probe":"Notices of Borrowing must be delivered before what time (Eastern time)?","golden":"1:00 p.m.","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m.\n"}]},{"eval_id":"019de200-d51b-7404-9feb-b6384f640f1a","probe":"How many calendar days prior to lease termination must the parties allow Lessor to enter the property for inspection?","golden":"60","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)\n"}]},{"eval_id":"019de200-d51c-7dd7-ad07-e2fd96baf505","probe":"Who conducted the Phase I Environmental Assessment mentioned in section 11.1?","golden":"GAIM REGIOMONTANA","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA\n"}]},{"eval_id":"019de200-d51d-7bbb-9bed-8ceaca14c398","probe":"What is the telephone number listed for Mr. Juan Carlos Gonzalez Quezada?","golden":"(81) 8358.7978","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8358.7978\n"}]},{"eval_id":"019de200-d51e-7caf-b475-352d47499736","probe":"What is the postal code (C.P.) listed in the address for Mr. Juan Carlos Gonzalez Quezada?","golden":"66220","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220\n"}]},{"eval_id":"019de200-d51f-723d-9741-37784d76009a","probe":"What is the telephone number listed for Mr. David Rodriguez Santos at Torre Sienna?","golden":"(81) 8356.1200","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(81) 8356.1200\n"}]},{"eval_id":"019de200-d520-7d78-a11e-ce881c0ff357","probe":"How many calendar days does Lessor have to object to a proposed sublease in writing?","golden":"30","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30\n"}]},{"eval_id":"019de200-d521-77a9-8367-9a4a834e7041","probe":"What is the apartment/interior number (Int.) listed in the address for Torre Sienna?","golden":"1403","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1403\n"}]},{"eval_id":"019de200-d522-7ac9-8bba-7b83fb15043b","probe":"What exhibit is the 'Maintenance Carnet' attached as?","golden":"Exhibit \"J\"","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\"\n"}]},{"eval_id":"019de200-d524-75fd-bff6-f429befeae8a","probe":"How many calendar days does Lessee have to dispute damages or Alterations indicated in Lessor's notice?","golden":"15","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15)\n"}]},{"eval_id":"019de22d-8775-7482-9f31-5e7710938d70","probe":"What is the original principal amount of the 3.50% Series A Convertible Senior Notes due February 1, 2018?","golden":"$70.3 million","png_sha":"9999d442e3243c2ea48a7de6c4c9b162568b4e59e41492087837bdb419a11d2c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million\n"}]},{"eval_id":"019de778-2487-7ceb-942f-bbc9cce683b5","probe":"What is the public law number?","golden":"118-109","png_sha":"a0300e50b30b31b24996ac843a50187dca0d8e81f6c026161ae3e07159e9815a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109\n"}]},{"eval_id":"019dfae7-e8c3-7289-a5e3-25d26a497795","probe":"What is the fiscal year end date?","golden":"September 28, 2024","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024\n"}]},{"eval_id":"019dfae8-2c75-7590-9083-4c07bf26944a","probe":"What is the Commission File Number?","golden":"001-36743","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743\n"}]},{"eval_id":"019dfae8-8300-75b0-98f0-558c886fd068","probe":"What is the registrant's telephone number?","golden":"(408) 996-1010","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010\n"}]},{"eval_id":"019dfae8-d37e-73db-bad0-7dbbebba1d87","probe":"What is the IRS Employer Identification Number?","golden":"94-2404110","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110\n"}]},{"eval_id":"019dfae9-3119-7c26-b2ed-73fb2888fdfe","probe":"What is the par value per share of Apple's common stock?","golden":"$0.00001","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001\n"}]},{"eval_id":"019dfae9-c244-75c3-92a8-4f02d64471e6","probe":"What were Americas net sales in 2024 (in millions)?","golden":"$167,045","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045\n"}]},{"eval_id":"019dfaea-1b4b-7bef-bf30-f8f1ee1cb9d6","probe":"What were Europe net sales in 2024 (in millions)?","golden":"$101,328","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328\n"}]},{"eval_id":"019dfaea-c282-7bca-85d8-a2edb7306504","probe":"What were total net sales in 2024 (in millions)?","golden":"$391,035","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035\n"}]},{"eval_id":"019dfaeb-1b0e-7077-a093-a8a138a79e25","probe":"What were Greater China net sales in 2022 (in millions)?","golden":"$74,200","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"74,200\n"}]},{"eval_id":"019dfaec-3d80-7c7c-95b7-6a34a086d48b","probe":"What is the date the report was signed?","golden":"November 1, 2024","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024\n"}]},{"eval_id":"019dfaec-8345-7eea-8840-6867945a7a06","probe":"Who is the Director and Chair of the Board?","golden":"Arthur D. Levinson","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ARTHUR D. LEVINSON\n"}]},{"eval_id":"019dfaec-e961-7051-a4ce-b66996997cb2","probe":"Who is the Senior Director of Corporate Accounting?","golden":"Chris Kondo","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo\n"}]},{"eval_id":"019dfaed-c27e-7590-9034-1cc2a5319b55","probe":"Who is the accounting firm that signed this consent?","golden":"Ernst & Young LLP","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP\n"}]},{"eval_id":"019dfaee-6467-74cc-8101-5271bea3e394","probe":"What is the Form S-8 number for the Apple Inc. Employee Stock Purchase Plan?","golden":"333-203698","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698\n"}]},{"eval_id":"019dfaf0-11d2-70d1-be50-371940478750","probe":"Where is Braeburn Capital, Inc. incorporated?","golden":"Nevada, U.S.","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S.\n"}]},{"eval_id":"019dfaf0-52d8-7941-b336-19bfbe7f8bc1","probe":"Where is Apple Asia Limited incorporated?","golden":"Hong Kong","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong\n"}]},{"eval_id":"019dfaf1-05a1-718d-818a-e45ba4945ba1","probe":"Where is Apple Operations Mexico, S.A. de C.V. incorporated?","golden":"Mexico","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico\n"}]},{"eval_id":"019dfaf2-2642-7eae-b1fb-1620be9706bc","probe":"Starting on what date does this policy apply to Incentive-Based Compensation that is Received?","golden":"October 2, 2023","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023\n"}]},{"eval_id":"019dfaf3-1977-7337-8a56-6b3d55edd900","probe":"What Nasdaq listing rule was adopted to implement Rule 10D-1 under the Exchange Act?","golden":"Listing Rule 5608","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608\n"}]},{"eval_id":"019dfaf3-d93a-7e7a-8293-bed401dc3c74","probe":"Under what year's Securities and Exchange Act is 'executive officer' defined for this policy?","golden":"1934","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934\n"}]},{"eval_id":"019dfaf4-6d06-7bb4-9da0-5703eced16ad","probe":"What company's logo appears at the top of this policy?","golden":"Apple","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple Inc.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple\n"}]},{"eval_id":"019dfaf5-67bd-727d-92f0-43a3108e55cf","probe":"What is the commission file number?","golden":"001-37580","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580\n"}]},{"eval_id":"019dfaf5-e414-73d4-a5bb-864069d83389","probe":"What is the IRS Employer Identification Number?","golden":"61-1767919","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919\n"}]},{"eval_id":"019dfaf6-3c67-7437-b33f-106a71df96cc","probe":"What is the registrant's telephone number?","golden":"(650) 253-0000","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000\n"}]},{"eval_id":"019dfaf6-8eaf-75f8-a68a-e019cf9ab6dc","probe":"What is the interest rate of the Senior Notes due 2064?","golden":"4.375%","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%\n"}]},{"eval_id":"019dfaf6-cd98-71f2-9576-0e07833ebd70","probe":"What is the interest rate of the Senior Notes due 2028?","golden":"2.375%","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%\n"}]},{"eval_id":"019dfaf7-7376-72e6-af9f-4f0302bf05aa","probe":"What is the trading symbol for Alphabet's Class C Capital Stock?","golden":"GOOG","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG\n"}]},{"eval_id":"019dfaf7-a3e9-7079-abc1-1170e6a73c4f","probe":"What is the fiscal year end date on this 10-K?","golden":"December 31, 2025","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"}]},{"eval_id":"019dfaf8-f7e3-7fa2-809d-07b2ec3cfaea","probe":"How much remained available for Class A and Class C share repurchases as of March 31, 2025?","golden":"$29.5 billion","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion\n"}]},{"eval_id":"019dfafa-9cb0-7412-8eac-d16591d94510","probe":"What is the quarterly cash dividend declared on April 2025?","golden":"$0.21","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21\n"}]},{"eval_id":"019dfafd-0e8d-7a0f-8f4e-4d3d489b698a","probe":"By what percentage did the Board of Directors increase the quarterly cash dividend in April 2025?","golden":"5%","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%\n"}]},{"eval_id":"019dfafe-5a0c-7b21-8bfa-72a257476e5a","probe":"What was the total carrying value of senior unsecured notes outstanding as of September 30, 2025?","golden":"$23.6 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion\n"}]},{"eval_id":"019dfaff-051e-7ba2-8350-09ebbfdb115a","probe":"How much remained available for Class A and Class C share repurchases as of September 30, 2025?","golden":"$74.8 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion\n"}]},{"eval_id":"019dfb00-8129-7fae-9c3d-085f17af7163","probe":"How many Class C shares were repurchased in the three months ended September 30, 2025 (in millions)?","golden":"51","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51\n"}]},{"eval_id":"019dfb01-6670-7c43-bf57-578d4e8743df","probe":"How much was the revolving credit facility expiring in April 2030?","golden":"$6.0 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion\n"}]},{"eval_id":"019dfb02-8211-7651-9ec4-8c0ebcf58a3b","probe":"What was the dollar amount of Class A share repurchases for the three months ended September 30, 2025 (in millions)?","golden":"$926","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926\n"}]},{"eval_id":"019dfb06-2d63-7e40-9cfc-442adddd3a61","probe":"As of what date did the CEO and CFO conclude on the disclosure controls evaluation?","golden":"June 30, 2025","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"}]},{"eval_id":"019dfb06-7255-7580-9ef1-58f24ae75626","probe":"What rule under the Exchange Act was used to evaluate disclosure controls and procedures?","golden":"Rule 13a-15","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15\n"}]},{"eval_id":"019dfb07-58e1-741b-95ae-39f6ad5b9738","probe":"For what quarter ended date is the internal control reporting statement made?","golden":"June 30, 2025","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025\n"}]},{"eval_id":"019dfb08-723b-72c9-8209-4c6b104c74d9","probe":"What form is the Quarterly Report on?","golden":"Form 10-Q","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q\n"}]},{"eval_id":"019dfb09-b2b4-7900-94d0-5ead62b5fa3a","probe":"How much was the initial investment used in the graph comparison?","golden":"$100","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"}]},{"eval_id":"019dfb0a-1542-7607-afff-3824643328be","probe":"On what date does the graph's tracking period end?","golden":"December 31, 2025","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025\n"}]},{"eval_id":"019dfb0a-4250-7161-8e90-fa2502ad8254","probe":"What is the starting date of the graph's tracking period?","golden":"December 31, 2020","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020\n"}]},{"eval_id":"019dfb0a-bbec-7b6d-bb26-274ff05f9459","probe":"What is the highest dollar value shown on the y-axis of the graph?","golden":"$400","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400\n"}]},{"eval_id":"019dfb0a-e54b-7973-8d05-99144d938deb","probe":"What color is the line representing the S&P 500 in the graph?","golden":"Green","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green\n"}]},{"eval_id":"019dfb0b-0fe9-717a-b315-903647d9114e","probe":"What color is the line representing Alphabet Inc. Class C in the graph?","golden":"Red","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"}]},{"eval_id":"019dfb0b-9664-7b20-bea5-647276953368","probe":"How much is Alphabet acquiring Wiz, Inc. for?","golden":"$32.0 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion\n"}]},{"eval_id":"019dfb0c-07a8-768c-bf46-7d82769ad116","probe":"What is the long-term income taxes payable as of December 31, 2025?","golden":"$9.5 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion\n"}]},{"eval_id":"019dfb0d-123a-74db-8a55-4a162b6b8cfb","probe":"How much is Alphabet acquiring Intersect for in cash?","golden":"$4.8 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion\n"}]},{"eval_id":"019dfb0d-98a6-7573-8987-ba32c57f6b7a","probe":"What is the total amount of purchase commitments and other contractual obligations as of December 31, 2025?","golden":"$149.1 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion\n"}]},{"eval_id":"019dfb14-6817-7cc7-90e2-fce76cd476e7","probe":"How many employees did JPMorganChase have globally as of December 31, 2025?","golden":"318,512","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512\n"}]},{"eval_id":"019dfb14-a085-7b52-8f76-6678f2a4de9c","probe":"How many employees does JPMorganChase have in North America?","golden":"185,208","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208\n"}]},{"eval_id":"019dfb14-f2e3-7cee-a27e-79e81867b37a","probe":"How many employees work in CCB?","golden":"144,196","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196\n"}]},{"eval_id":"019dfb15-3908-7fc5-93bd-052705ae9929","probe":"In how many countries are JPMorganChase's employees located?","golden":"66","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"}]},{"eval_id":"019dfb15-75a7-7c29-a2ca-90c32df63ac5","probe":"What percentage of total employees are women?","golden":"48%","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%\n"}]},{"eval_id":"019dfb15-c7c7-74ee-b29b-e7b5d8c9a152","probe":"How many employees work in the Asia-Pacific region?","golden":"96,499","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499\n"}]},{"eval_id":"019dfb16-cbe3-7d4d-a23d-2234c2d7d297","probe":"What is the first bulleted item under the list of electronic and internet-based financial solutions?","golden":"lending and other extensions of credit to consumers","png_sha":"704943f48019c6bab8cb509e1ddeb6f9b48085007ac9101976ed3d04798ac274","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers\n"}]},{"eval_id":"019dfb17-0cc4-74a1-8d62-afab29ef1e82","probe":"What is the third bulleted item under the list of electronic and internet-based financial solutions?","golden":"cryptocurrency, including stablecoins","png_sha":"704943f48019c6bab8cb509e1ddeb6f9b48085007ac9101976ed3d04798ac274","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins\n"}]},{"eval_id":"019dfb18-cb9a-7558-a5ce-7b4911abc1ba","probe":"What was the total assets under management in 2025 (in billions)?","golden":"$4,791","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791\n"}]},{"eval_id":"019dfb19-eada-7639-80c1-d416915f2795","probe":"How many client advisors were there as of December 31, 2025?","golden":"10,150","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10,150\n"}]},{"eval_id":"019dfb1a-7fed-744e-a7bc-585de30578fb","probe":"What was the equity assets value in 2025 (in billions)?","golden":"$1,400","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400\n"}]},{"eval_id":"019dfb1a-d4b4-7ee1-b950-3f3208c24be4","probe":"What was the reported net interest income in 2025 (in millions)?","golden":"$95,443","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95,443\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95,443\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95,443\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95,443\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"95,443\n"}]},{"eval_id":"019dfb1b-4a0a-766a-92cd-c2e37df27c36","probe":"What was the net yield on average interest-earning assets on a managed basis in 2025?","golden":"2.50%","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50 %\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50 %\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50 %\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\n"}]},{"eval_id":"019dfb1b-9e1c-704c-b958-e7a06540c65f","probe":"What was the Memo: Total Markets net revenue in 2025 (in millions)?","golden":"$35,782","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35,782\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35,782\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35,782\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35,782\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35,782\n"}]},{"eval_id":"019dfb1c-4c58-739f-8241-e4a688fff415","probe":"What was the noninterest revenue excluding Markets in 2023 (in millions)?","golden":"$44,361","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361\n"}]},{"eval_id":"019dfb1d-0b1b-7540-9211-41f0ac069d15","probe":"In what year was MetLife, Inc. incorporated in Delaware?","golden":"1999","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999\n"}]},{"eval_id":"019dfb1d-fe01-7745-a248-c6531ebdce43","probe":"What act is referenced as the source of the 'forward-looking statements' definition?","golden":"Private Securities Litigation Reform Act of 1995","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995\n"}]},{"eval_id":"019dfb1e-4042-7d24-95d6-9213cb5fb946","probe":"How many factors are listed on this page?","golden":"22","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22\n"}]},{"eval_id":"019dfb1e-d54d-73fd-8f17-16eb21390c86","probe":"What is factor number 10 in the list?","golden":"London Interbank Offered Rate discontinuation and transition to alternative reference rates","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates\n"}]},{"eval_id":"019dfb1f-5f66-79ad-be34-3c4e429dbcac","probe":"How old is Steven J. Goulart?","golden":"64","png_sha":"8a8df5c53ffc88bd982b700c7adc729d6f1a78da7ebcbf1ee0a1a778e2017590","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64\n"}]},{"eval_id":"019dfb23-8371-717a-825f-6e20e45dcb5f","probe":"What is the U.S. segment's percentage contribution to total segment level adjusted earnings?","golden":"47%","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%\n"}]},{"eval_id":"019dfb29-7d6d-77ed-abe1-9e196503fe98","probe":"What is American Life Insurance Company's Moody's rating?","golden":"A1","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1\n"}]},{"eval_id":"019dfb29-d233-7190-9c54-414c50184509","probe":"What is Metropolitan Life Insurance Company's Fitch rating?","golden":"AA-","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-\n"}]},{"eval_id":"019dfb2a-30eb-73bc-9534-9a1a79fcefd9","probe":"What is Metropolitan Tower Life Insurance Company's Moody's rating?","golden":"Aa3","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3\n"}]},{"eval_id":"019dfb3c-0056-7fd4-8497-80ad7e52deed","probe":"What is the date on the letter?","golden":"September 12, 2025","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025\n"}]},{"eval_id":"019dfb3c-443c-749d-9922-e22f48da574a","probe":"What is the total amount of expenses stated in the letter?","golden":"$537.6 billion","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion\n"}]},{"eval_id":"019dfb3c-e409-7e70-93e0-584a7b66e218","probe":"What is the fax number listed at the bottom of the letter?","golden":"916.322.4404","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404\n"}]},{"eval_id":"019dfb3d-df1d-70c3-8680-871f110c4e18","probe":"How many state departments are involved in the ACFR production, according to the letter?","golden":"more than 200","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"more than 200\n"}]},{"eval_id":"019dfb41-090f-742c-a295-a841b0d40942","probe":"What is the last year the ACFR publication target date in March was achieved, according to the letter?","golden":"2018","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018\n"}]},{"eval_id":"019dfb42-0697-72fe-ace9-658c5975fe72","probe":"What is the General fund balance as previously reported on 6/30/2023?","golden":"$64,003,688","png_sha":"4d385e9f1f0ded0edf6cd42e1fce98d308714a9c9a90264d60830da6a87b20a5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688\n"}]},{"eval_id":"019dfb42-9508-70e6-ba0b-e32a83de1982","probe":"What is the Pension/OPEB balance as previously reported on 6/30/2023?","golden":"$826,165,564","png_sha":"4d385e9f1f0ded0edf6cd42e1fce98d308714a9c9a90264d60830da6a87b20a5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564\n"}]},{"eval_id":"019dfb45-c922-797e-8c28-c8e8919e6e6b","probe":"What was the General Fund's ending fund balance for fiscal year 2023-24?","golden":"$63.4 billion","png_sha":"be9e4b96b82c2251ae314ddc72ad643547069399fbff67cb23663b4b60410b07","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$63.4 billion\n"}]},{"eval_id":"019dfb48-c7e6-72a9-8f31-8e936894de0c","probe":"What was the total primary government net position in 2006 (in thousands)?","golden":"$48,552,143","png_sha":"6ded8b72d8724efb0a5addcabb85b9fb055c8702b034b32a8bd9d35ae7b3b2d4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"}]},{"eval_id":"019dfb49-36d0-787d-9b10-263d0dc86158","probe":"What was the total business-type activities net position in 2005 (in thousands)?","golden":"$9,638,143","png_sha":"6ded8b72d8724efb0a5addcabb85b9fb055c8702b034b32a8bd9d35ae7b3b2d4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 9,638,143"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9,638,143"}]},{"eval_id":"019dfb49-c621-751e-8311-221426895f61","probe":"What date does the fiscal year end?","golden":"June 30, 2013","png_sha":"e78f4e20277a031b7f8a1c8ec01e35359d5db802026c772a280aa46b2e15036d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013\n"}]},{"eval_id":"019dfb4a-c5b5-77b8-8666-73fe5ecf7295","probe":"What word appears on the banner above the figure in the seal?","golden":"EUREKA","png_sha":"e78f4e20277a031b7f8a1c8ec01e35359d5db802026c772a280aa46b2e15036d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA\n"}]},{"eval_id":"019dfb4c-a89f-7747-8ca3-fb374afbe129","probe":"How many employees were in the Services industry in 2012?","golden":"6,219,000","png_sha":"ee102138e4471a718761ff29297490e756f20be442c4eab71f74ad7b88ef9337","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000\n"}]},{"eval_id":"019dfb4d-3d6b-7988-bb66-c81ee4e34bf7","probe":"How many employees were in Manufacturing in 2003?","golden":"1,544,500","png_sha":"ee102138e4471a718761ff29297490e756f20be442c4eab71f74ad7b88ef9337","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500\n"}]},{"eval_id":"019dfff9-bbf0-7f8f-9eeb-4283d498732d","probe":"What is the General Fund amount due from primary government to University of California?","golden":"$169,215","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"169,215\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215\n"}]},{"eval_id":"019dfffa-4c63-71d9-9bae-44bb0f5d067a","probe":"What is the total primary government amount due to component units?","golden":"$209,125","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"209,125\n"}]},{"eval_id":"019dfffa-9fa6-7a63-a87b-53eda9047796","probe":"What is the amount from Nonmajor governmental funds due to University of California?","golden":"36,988","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988\n"}]},{"eval_id":"019dfffb-b244-7a37-903d-2e6addf12282","probe":"What was the net general bonded debt per capita in 2018?","golden":"$2,042","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042\n"}]},{"eval_id":"019dfffc-0d62-7f14-a566-4e70db84b399","probe":"What was the net general bonded debt as a percentage of personal income in 2015?","golden":"4.0%","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%\n"}]},{"eval_id":"019dfffc-678a-79c5-aaea-473c3f22a054","probe":"What was the General obligation bonds amount in 2017?","golden":"$79,503,871","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79,503,871\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871\n"}]},{"eval_id":"019dfffc-e4bf-79ad-8c4e-89d704ac54ed","probe":"What is at the top of the Texas government structure chart?","golden":"The Electorate","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate\n"}]},{"eval_id":"019dfffe-6b06-706f-a135-e5934397dcc8","probe":"What body sits directly below the Legislature on the chart, alongside the State Auditor's Office?","golden":"Legislative Committees","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees\n"}]},{"eval_id":"019dffff-a90b-7567-a8fa-d73e11996c14","probe":"What body is shown at the very bottom of the Legislative branch chart?","golden":"Sunset Advisory Commission","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission\n"}]},{"eval_id":"019e0000-52c3-755e-9a98-534e00107784","probe":"What is the total pass-through to other agencies?","golden":"$254,334.30","png_sha":"cee789f33becc6e55d762115a7b119808f36099b5c736f4b0ec740bce52a004c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30\n"}]},{"eval_id":"019e0001-dddd-7fec-b736-f93ff293500f","probe":"What was the balance in the ESF fund on Aug. 31, 2024?","golden":"$23.8 billion","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion\n"}]},{"eval_id":"019e0002-846c-7a5c-bcd2-21cf9dab8b63","probe":"What was the Texas unemployment rate as of November 2024?","golden":"4.2 percent","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent\n"}]},{"eval_id":"019e0003-4dd3-73ec-8ba4-bf652587ad06","probe":"By how much is Texas' population projected to grow in 2025?","golden":"376,600","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600\n"}]},{"eval_id":"019e0008-27fa-70f4-8421-41777f7bcace","probe":"What office is shown in pink under the First Deputy Mayor?","golden":"Office of Efficiency","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency\n"}]},{"eval_id":"019e0009-2f8e-768d-8762-ff9e82bcea2b","probe":"What is the SAO Report Number?","golden":"25-316","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316\n"}]},{"eval_id":"019e000b-d49b-7660-82c4-81ecfb04a236","probe":"What percentage of revenue comes from Charges for Services in Graph MDA-6?","golden":"59.7%","png_sha":"3f8e2c78a2134ddb79f740cc731c989a29e5b11d89cdb0254e1f1740d44cfdb0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%\n"}]},{"eval_id":"019e000d-e61a-7a45-b84f-1c881c74e271","probe":"What is the fair value of Private Equity investments (in thousands)?","golden":"$76,309,756","png_sha":"1993d56fb3f7471f5844aa6a62bb8dd9a43b4784dac30f107664bca458bf68ea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756\n"}]},{"eval_id":"019e000e-f859-77f7-aa7c-927c51e130e8","probe":"What is the unfunded commitment for Energy, Natural Resources, Infrastructure (in thousands)?","golden":"$11,460,123","png_sha":"1993d56fb3f7471f5844aa6a62bb8dd9a43b4784dac30f107664bca458bf68ea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123\n"}]},{"eval_id":"019e0010-c825-72aa-a139-0e4ab295b2dc","probe":"What is the minimum aggregate floor area required by the CEP program?","golden":"25,000 square feet","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet\n"}]},{"eval_id":"019e0011-2a92-7ac7-89be-ac4f2296baea","probe":"Under the CRP/CEP programs, by how much were the City's tax revenues reduced in 2024 (in thousands)?","golden":"$12,500","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"}]},{"eval_id":"019e0011-cff1-7126-8235-02b26f0fbab9","probe":"What year did ICAP replace ICIP?","golden":"2008","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008\n"}]},{"eval_id":"019e0017-450f-737d-a346-38c48007c835","probe":"Under the CRP program, what is the per-square-foot dollar amount used in the base abatement calculation formula?","golden":"$2.50","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50\n"}]},{"eval_id":"019e0018-17a0-7847-a0b3-11f039bc48a6","probe":"What is the page number shown at the bottom of this page?","golden":"128","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128\n"}]},{"eval_id":"019e0019-d170-7146-8e38-cc44276e6018","probe":"Under the CRP/CEP programs, by how much were the City's tax revenues reduced as a result of abatement agreement in 2024 (in thousands)?","golden":"$12,500","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500\n"}]},{"eval_id":"019e001b-3183-79f1-a745-4e066a6ce3ef","probe":"What is the Executive Order number mentioned in the letter?","golden":"2025-1","png_sha":"781c6fcbd4f3164179bf71cd942ca2e9794fc7c49c6bbcf883dd13f2ce626331","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1\n"}]},{"eval_id":"019e001b-77bc-7c11-843b-51dfbbec15c3","probe":"Who signed this letter?","golden":"Mayor Brandon Johnson","png_sha":"781c6fcbd4f3164179bf71cd942ca2e9794fc7c49c6bbcf883dd13f2ce626331","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson\n"}]},{"eval_id":"019e001d-d405-7881-ab8b-abcb0d7e70e1","probe":"What is Deloitte's fax number listed on the page?","golden":"+1 312 486 1486","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486\n"}]},{"eval_id":"019e001f-f83d-78ad-bad5-21b87bdb9833","probe":"According to the auditor's report, the Pension Trust Funds represent what percentages of the assets, financial position, and revenues respectively?","golden":"92%, 100%, and 72%","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%\n"}]},{"eval_id":"019e0020-bffb-7733-931f-63dac6e0f8f0","probe":"Who is the report addressed to as Mayor?","golden":"Brandon Johnson","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson\n"}]},{"eval_id":"019e0027-f41a-7a7a-b3f6-f9b59cde341b","probe":"What is the experience study period for the Policemen's plan?","golden":"January 1, 2019 - December 31, 2023","png_sha":"2aded5f520cbaa023e8d0c1e94f15e68ccafa9f34d1e6736781e6f894512fe8e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023\n"}]},{"eval_id":"019e0028-b45f-7292-959c-f04db8d08d19","probe":"What is the experience study period for the Laborers' plan?","golden":"January 1, 2017 - December 31, 2019","png_sha":"2aded5f520cbaa023e8d0c1e94f15e68ccafa9f34d1e6736781e6f894512fe8e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019\n"}]},{"eval_id":"019e002e-34d1-7c51-ba48-bffeca76fb26","probe":"What was the loans receivable balance of the CCCF as of December 31, 2024?","golden":"$3.1 million","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$3.1 million\n"}]},{"eval_id":"019e002e-ef48-7527-8160-cb77c6e44245","probe":"On what date did the City of Chicago City Council adopt the ordinance organizing the STSC?","golden":"October 11, 2017","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017\n"}]},{"eval_id":"019e0030-d1da-7720-bec1-d70663e3456a","probe":"On what date did the City Council adopt the CCCF Ordinance?","golden":"November 16, 2016","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016\n"}]},{"eval_id":"019e0033-8f40-79d7-8505-50112ded8060","probe":"What is the website where complete financial statements of the STSC can be obtained?","golden":"www.salestaxsecuritizationcorporation.com","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com\n"}]},{"eval_id":"019e003a-5da3-7d08-9f15-665248ccb0cf","probe":"What was the final budgeted Vehicle Tax amount under Transportation Tax (in thousands)?","golden":"$128,777","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777\n"}]},{"eval_id":"019e003a-e619-7c9f-b4b2-aa2807d3bff9","probe":"What was the actual Motor Fuel Tax and Project revenue under Transportation Tax (in thousands)?","golden":"$122,483","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483\n"}]},{"eval_id":"019e003c-6cc9-782c-bca0-875bef94c76c","probe":"What was the final budgeted MEABF Pension Reserve under Special Area and Utility Taxes (in thousands)?","golden":"$216,275","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275\n"}]},{"eval_id":"019e003d-55d2-7007-b3b6-dc37892643d2","probe":"Who is the Chief Actuary?","golden":"Marek Tyszkiewicz","png_sha":"89c77daf9c6f881f0116f445cbf736cffc12698b60a93b437699a1a075b00138","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz\n"}]},{"eval_id":"019e003f-44df-7a8d-a15c-ff2dc3cf553b","probe":"What is the funded ratio for the 2022 valuation date?","golden":"85.1%","png_sha":"13c08f8d02fa78d2fc1f1b9783d494af4a43f3083f75509ffac06a9ae415320f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%\n"}]},{"eval_id":"019e0040-0266-795a-b6d2-549f195f8032","probe":"What percentage of the Police Superior Officers' Variable Supplements Fund is held in Collective Trust Funds?","golden":"59.28%","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%\n"}]},{"eval_id":"019e0040-6668-7abd-8cd8-dd05d069c1c1","probe":"What is the dollar amount of Equity Securities in the Police Officers' Variable Supplements Fund?","golden":"$771,119","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119\n"}]},{"eval_id":"019e0041-2237-71d4-8880-cb8564c7b0ae","probe":"What is the dollar amount of Short-Term Investments in the Police Superior Officers' Variable Supplements Fund?","golden":"$8,441","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441\n"}]},{"eval_id":"019e0042-1c07-71d9-8683-e990abab4862","probe":"What is the Reduced Service Retirement probability at 20 years of service?","golden":"5.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"}]},{"eval_id":"019e0043-db39-746e-8a90-d9b8e9e16e2f","probe":"What is the Unreduced Before Full Escalation probability at 22 years of service?","golden":"5.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%\n"}]},{"eval_id":"019e0044-11fe-7039-99f0-4014e1cca342","probe":"What is the Reduced Service Retirement probability at 21 years of service?","golden":"2.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%\n"}]},{"eval_id":"019e0045-18ce-7ff9-90d3-7a8a76d3a7b2","probe":"What is the As Restated Total Liabilities amount?","golden":"54,689,670","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670\n"}]},{"eval_id":"019e0046-8a1d-76f7-a894-dfdf17c5e779","probe":"What is the As Previously Stated Unrestricted (Deficit) amount (in thousands of dollars)?","golden":"(33,888,893)","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)\n"}]},{"eval_id":"019e0048-5d8d-7e41-bfac-807538f6bc7d","probe":"What is the required year of adoption for GASB Statement No. 102?","golden":"2025","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025\n"}]},{"eval_id":"019e0049-7334-7204-a87d-cdd77f11d1df","probe":"What is the As Restated Total Net (Deficit)/Position amount (in thousands)?","golden":"$(30,877,248)","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)\n"}]},{"eval_id":"019e004a-3183-7f93-ae28-888547cf9f69","probe":"What is the As Previously Stated Accrued and Other Liabilities amount (in thousands)?","golden":"$2,037,352","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352\n"}]},{"eval_id":"019e004b-c349-7e93-af8d-24a8c0227413","probe":"Who is the Chairman of the Texas Transportation Commission?","golden":"J. Bruce Bugg, Jr.","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr.\n"}]},{"eval_id":"019e004c-1788-7c26-832d-effce8fee9e9","probe":"What city is Commissioner Robert C. Vaughn from?","golden":"Dallas","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas\n"}]},{"eval_id":"019e004c-7b29-737b-b3c2-4cb5677b686a","probe":"What city is Commissioner Steven D. Alvis from?","golden":"Houston","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\n"}]},{"eval_id":"019e004e-6fac-7e8f-a9ed-7aab75af118d","probe":"What is the Total Foreign Currency Risk for Fiduciary Funds (in thousands)?","golden":"$454,100","png_sha":"14dd94971a85d5333d42a72d87ae42c4f4cf19684f10114f6d12e3dc0dcfbba3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 454,100\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 454,100\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 454,100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 454,100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100\n"}]},{"eval_id":"019e004f-570b-7494-b4dc-1980043719cb","probe":"What is the Component Units amount for Uninsured and Uncollateralized in Table 3A (in thousands)?","golden":"$729,847","png_sha":"14dd94971a85d5333d42a72d87ae42c4f4cf19684f10114f6d12e3dc0dcfbba3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 729,847\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 729,847\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 729,847\n"}]},{"eval_id":"019e0050-7b43-7b4a-b132-8ba0d44ecc08","probe":"What is the Total Fund Balance \u2013 Governmental Funds (in thousands)?","golden":"$98,174,085","png_sha":"2e5b15b0fe9ca40f66bc4f99fea40f7e0fb26c9abe4ac75ea6dad2ab72ae36d6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98,174,085\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 98,174,085\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 98,174,085\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"98,174,085\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 98,174,085\n"}]},{"eval_id":"019e007c-e48c-710f-9404-90a2a810ccb4","probe":"What is the Net Position of Governmental Activities (in thousands)?","golden":"$134,878,410","png_sha":"2e5b15b0fe9ca40f66bc4f99fea40f7e0fb26c9abe4ac75ea6dad2ab72ae36d6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134,878,410\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 134,878,410\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134,878,410\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410\n"}]},{"eval_id":"019e007d-9a24-752a-89d4-7fe852700caa","probe":"What is the total revenue shown in the Revenue by Source pie chart?","golden":"$190.5 Billion","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion\n"}]},{"eval_id":"019e007e-1a80-7e4b-98c2-9c3f2d812c06","probe":"What percentage of revenue came from Taxes?","golden":"42.7%","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%\n"}]},{"eval_id":"019e007e-aac9-7785-8c44-edb9f9dfe20d","probe":"What are the total expenses across all governmental activities?","golden":"$154,896","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 154,896\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 154,896\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 154,896\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 154,896\n"}]},{"eval_id":"019e007f-3589-7306-b64b-6253528585e4","probe":"What page is Risk Factors on?","golden":"14","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14\n"}]},{"eval_id":"019e007f-7683-7d10-a251-ff6bdde0aca0","probe":"What page is Executive Compensation on?","golden":"105","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105\n"}]},{"eval_id":"019e007f-b345-710c-b63d-5812e55e82ef","probe":"What page is Financial Statements and Supplementary Data on?","golden":"48","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48\n"}]},{"eval_id":"019e0080-81ba-7bac-bba1-8cc2e8324436","probe":"What page is the Budgetary Comparison \u2013 General Fund on?","golden":"47","png_sha":"0a460adc7db810670c579dc36d27c02a4097bb3e02f77fbbeacd84bbcc9d2f0e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47\n"}]},{"eval_id":"019e0080-b0bf-7f30-a02e-a2ed8dcea371","probe":"What page is the Schedule of Employee Benefits \u2013 All Funds on?","golden":"56","png_sha":"0a460adc7db810670c579dc36d27c02a4097bb3e02f77fbbeacd84bbcc9d2f0e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\n"}]},{"eval_id":"019e0081-ed0a-7c3a-a9ba-53b6b5920008","probe":"What word is shown as a watermark across the map?","golden":"DRAFT","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT\n"}]},{"eval_id":"019e0082-3d98-723b-b6b4-132e744dab15","probe":"Which county is labeled at the bottom-right area of the map, below Ellis?","golden":"Navarro","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAVARRO\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAVARRO\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Navarro\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAVARRO\n"}]},{"eval_id":"019e0083-0a96-77f4-a106-fb583482c798","probe":"How much did the General Land Office (GLO) increase?","golden":"$860 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand\n"}]},{"eval_id":"019e0083-5461-7354-8851-9512e63b1c22","probe":"How much did the Texas Commission on Environmental Quality (TCEQ) increase?","golden":"$543 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand\n"}]},{"eval_id":"019e0083-c942-7b97-83f8-c0423a20e2a4","probe":"How much did the Federal Emergency Management Agency (FEMA) decrease?","golden":"$420 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand\n"}]},{"eval_id":"019e0084-65de-77d8-92f6-79df23bc1fad","probe":"What is the phone number for Pattillo, Brown & Hill, L.L.P.?","golden":"254.772.4901","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901\n"}]},{"eval_id":"019e0084-dffc-7ecf-b0c1-44b81836ebdd","probe":"What is the date of the year ended for the audit?","golden":"September 30, 2024","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024\n"}]},{"eval_id":"019e009f-5030-795d-b32e-68b8c8725b1a","probe":"What is the page number shown at the bottom right?","golden":"H261","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H261\n"}]},{"eval_id":"019e00a0-6d47-7a01-8cdb-9db00cf90181","probe":"Which bill number is referenced as the 'Born-Alive Abortion Survivors Protection Act'?","golden":"H.R. 21","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H.R. 21\n"}]},{"eval_id":"019e00a1-03cf-7de0-9353-8ede1f29d21e","probe":"What time did the House meet?","golden":"10 a.m.","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m.\n"}]},{"eval_id":"019e00a2-46eb-7c4d-93dc-be4b015c5931","probe":"Until what time may morning-hour debate continue?","golden":"11:50 a.m.","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m.\n"}]},{"eval_id":"019e00a2-8827-7350-ac1d-d1e691c7bc93","probe":"Which Congress's proceedings does this issue cover?","golden":"119th","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th\n"}]},{"eval_id":"019e00a3-4654-7104-90ff-d36264aea63f","probe":"Who did Speaker Mike Johnson appoint as Speaker pro tempore for the day?","golden":"Nathaniel Moran","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nathaniel Moran\n"}]},{"eval_id":"019e00a4-39cf-73f5-a08d-bdaf6f0e9555","probe":"Which state is Mrs. Trahan from?","golden":"Massachusetts","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts\n"}]},{"eval_id":"019e00a4-9927-7270-b177-688639d2d84a","probe":"Which state is Mr. Thompson from?","golden":"Pennsylvania","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania\n"}]},{"eval_id":"019e00a5-86fd-7ef3-9421-534e8a66b6ef","probe":"How many 'yeas' were there in Roll No. 20?","golden":"214","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214\n"}]},{"eval_id":"019e00a5-ff31-72d6-b137-910bed3336e6","probe":"How many representatives were 'not voting' in Roll No. 20?","golden":"15","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"}]},{"eval_id":"019e00a6-329c-73a0-9a01-cd95583196e9","probe":"How many 'nays' were there in Roll No. 20?","golden":"204","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204\n"}]},{"eval_id":"019e00a7-701e-7774-bdaa-4a60fe45e545","probe":"What is the page number shown at the top left?","golden":"H276","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276\n"}]},{"eval_id":"019e00a7-fb7c-797d-8520-954d5503a748","probe":"What is the Roll number for the vote shown on this page?","golden":"20","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20\n"}]},{"eval_id":"019e00ac-04dd-7f1d-bcec-9be7f5c1f3ce","probe":"Did Aderholt vote yea or nay?","golden":"yea","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"}]},{"eval_id":"019e00ac-a893-7e85-9fc2-0de0e7d020dd","probe":"Did Cherfilus-McCormick vote yea or nay?","golden":"nay","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"}]},{"eval_id":"019e00ac-faaf-7e38-b571-92ff92b76932","probe":"Garcia of California voted in which column?","golden":"NAYS","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"NAYS\n"}]},{"eval_id":"019e00ad-32af-76df-9057-a199ce91dd17","probe":"How many \"Garcia\" members are listed in the NAYS column?","golden":"3","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"}]},{"eval_id":"019e00ad-d3ed-7216-853a-30e02dbd1131","probe":"Who is the first name listed alphabetically in the NAYS column?","golden":"Adams","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams\n"}]},{"eval_id":"019e00ae-10e5-7c6b-956c-c30654f0adda","probe":"What is the last name listed in the YEAS column?","golden":"Zinke","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Zinke\n"}]},{"eval_id":"019e00b0-cecb-7e7c-8149-7640c1dad861","probe":"Which member changed their vote from \"nay\" to \"yea\"?","golden":"Mr. Palmer","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Palmer\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER\n"}]},{"eval_id":"019e00b3-c235-73fb-ba21-0118c8eadbf3","probe":"What is the page number shown in the top-left corner?","golden":"S250","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250\n"}]},{"eval_id":"019e00b4-9c27-73de-8223-11187c914c6f","probe":"What is the date shown at the top-right of the page?","golden":"January 20, 2025","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025\n"}]},{"eval_id":"019e00b9-b13c-7e4a-bf11-475eea29d6d3","probe":"Did Senator McConnell vote yea or nay on the final passage of S. 5?","golden":"yea","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"}]},{"eval_id":"019e00bb-59ee-702a-8cec-38e372b26db8","probe":"How many senators voted YEA on Amendment No. 8?","golden":"75","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75\n"}]},{"eval_id":"019e00bb-a83a-79e5-808d-25352081e864","probe":"How many senators voted NAY on the final passage of S. 5?","golden":"35","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35\n"}]},{"eval_id":"019e00bc-df61-7504-ab8f-56af050077d7","probe":"Who is being considered for Secretary of State on Executive Calendar No. 2?","golden":"Marco Rubio","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO\n"}]},{"eval_id":"019e00bf-a471-719a-84c8-972702dced95","probe":"What dollar amount is mentioned as the threshold for financial harm to a State or its residents?","golden":"$100","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100\n"}]},{"eval_id":"019e00c1-687b-7e30-917e-677d5c514e5a","probe":"Who asked for the yeas and nays on the vote for S. 5?","golden":"Mrs. Britt","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. BRITT\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mrs. Britt\n"}]},{"eval_id":"019e00c1-d9d4-7426-9471-e13471bf2c6f","probe":"How many nays were there on the vote on Amendment No. 8?","golden":"24","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24\n"}]},{"eval_id":"019e00c6-1e73-73ec-8e95-413c88e39426","probe":"How much did the Wesley Hunt Victory Fund contribute on 2/3/2025?","golden":"$25,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"}]},{"eval_id":"019e00c6-5871-7da2-a93b-3aefb5c66f16","probe":"What is the page number shown at the top left?","golden":"S2714","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714\n"}]},{"eval_id":"019e00c8-3f2a-7e4f-b0e4-86c796356894","probe":"How much did the Connecticut Republican State Central Committee transfer on 9/27/2024?","golden":"$10,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00\n"}]},{"eval_id":"019e00c9-4d63-7e78-a3b2-fd24f554e0db","probe":"What was the largest single contribution amount listed in the Spouse section?","golden":"$25,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000.00\n"}]},{"eval_id":"019e00c9-c213-7e12-b66f-043b2559c706","probe":"Who is being nominated to be Lieutenant Commander in the Coast Guard?","golden":"John O. Mansolillo","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo\n"}]},{"eval_id":"019e00ce-9d49-7844-bd6c-346e75c0b284","probe":"What is the bill number for the bill to direct the Secretary of the Treasury to stop minting the penny?","golden":"S. 1525","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\n"}]},{"eval_id":"019e0518-b40f-7b97-99f0-2cd141711ff0","probe":"What is the bill number for the bill to regulate assault weapons?","golden":"S. 1531","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1531\n"}]},{"eval_id":"019e051c-6f18-78b3-a1d7-9d8a0a2b9618","probe":"How many senators voted yea on the Driscoll nomination?","golden":"66","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66\n"}]},{"eval_id":"019e051d-3c27-7462-be35-0be6eece26b9","probe":"How many senators were listed as NOT VOTING?","golden":"6","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"}]},{"eval_id":"019e051d-a887-715d-88bf-933cc563b087","probe":"How many nays were there in the vote?","golden":"28","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28\n"}]},{"eval_id":"019e051e-38d3-7d68-9805-50585c912e12","probe":"How would Senator Cruz of Texas have voted if present?","golden":"yea","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea\n"}]},{"eval_id":"019e0520-d920-72fd-9146-7ff4401c225d","probe":"Did Senator Booker vote yea or nay on the Driscoll nomination?","golden":"nay","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay\n"}]},{"eval_id":"019e0523-07a2-7eed-a522-32a019057e4b","probe":"Under what clause and rule were sponsors added to public bills?","golden":"clause 7 of rule XII","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII\n"}]},{"eval_id":"019e0524-2f26-7e2d-b1d6-9d9e4787d2c7","probe":"How many additional sponsors were added to H.R. 21?","golden":"8","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"}]},{"eval_id":"019e0524-a11c-7139-bf9b-71cd8bf76e24","probe":"Who was added as a sponsor to H.R. 247?","golden":"Ms. Omar","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. OMAR\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Omar\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. OMAR\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. OMAR\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. OMAR\n"}]},{"eval_id":"019e0525-2888-7fab-bbe4-24c066ee419f","probe":"Who was added as a sponsor to H.R. 31?","golden":"Mr. Stauber","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Stauber\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. STAUBER\n"}]},{"eval_id":"019e0529-025b-7daa-a5e9-a453809b33ba","probe":"How many sponsors were added to H. Res. 23?","golden":"15","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15\n"}]},{"eval_id":"019e0529-5749-7c17-9f42-70fde0a280ae","probe":"Who was added as a sponsor to H.R. 438?","golden":"Ms. Malliotakis","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. MALLIOTAKIS\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. Malliotakis\n"}]},{"eval_id":"019e0529-ab42-7f49-b945-e7fa7946e4e8","probe":"Who was added as a sponsor to H.R. 493?","golden":"Ms. DelBene","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DELBENE\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ms. DelBene\n"}]},{"eval_id":"019e053e-4d48-7017-b80c-96993dddb76d","probe":"How many patients were in the SOC alone group?","golden":"4,321","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"}]},{"eval_id":"019e053f-1f3f-7cd4-9bdf-bb8319b59261","probe":"What is the table number and title?","golden":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data\n"}]},{"eval_id":"019e0540-facb-7b6a-8fd8-3f509341da68","probe":"What was the mean age of participants in the RECOVERY trial?","golden":"66 years","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years\n"}]},{"eval_id":"019e0541-5acc-73a2-a0f0-4a8a3fd3f3d7","probe":"When was this table last updated?","golden":"February 29, 2024","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024\n"}]},{"eval_id":"019e0542-7270-77f1-aa19-55066dadd841","probe":"How many patients were in the SOC alone group?","golden":"4,321","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\n"}]},{"eval_id":"019e0543-15cb-749c-890f-dc25b546fa1f","probe":"What percentage of participants had laboratory-confirmed SARS-CoV-2 infection?","golden":"89%","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%\n"}]},{"eval_id":"019e0547-98af-7c91-aa30-6a7096eca524","probe":"What is the table number and title shown at the top of the page?","golden":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19\n"}]},{"eval_id":"019e0547-eecc-7d07-95de-24c48450b6a5","probe":"On what date was this document downloaded according to the bottom of the page?","golden":"3/1/2024","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"}]},{"eval_id":"019e0549-117f-704c-b2ed-3771bcbf57de","probe":"What is the URL shown at the bottom of the page where this document was downloaded from?","golden":"https://www.covid19treatmentguidelines.nih.gov/","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/\n"}]},{"eval_id":"019e054a-48f1-7ae1-8c9a-f98de9d0fa5b","probe":"What is the recommendation for patients hospitalized but not requiring supplemental oxygen who are at high risk of progressing to severe COVID-19?","golden":"Remdesivir","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir\n"}]},{"eval_id":"019e0550-1990-7266-9919-560f19c4cee5","probe":"In the CATCO trial, what percentage of patients received corticosteroids?","golden":"87%","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%\n"}]},{"eval_id":"019e0550-c523-7e3c-a7bb-5e58b208e5dc","probe":"In the CATCO trial, what percentage of patients were on conventional oxygen?","golden":"54%","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%\n"}]},{"eval_id":"019e0553-86d1-71ca-b900-5bbaabb7ca45","probe":"How many randomized controlled trials were included in the pooled analysis of individual data mentioned with ACTT-1?","golden":"9","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9\n"}]},{"eval_id":"019e0555-7910-7ed7-a44b-456f65b6a4b0","probe":"Approximately what fraction of patients in the Solidarity trial received corticosteroids?","golden":"two-thirds","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"approximately two-thirds\n"}]},{"eval_id":"019e055a-07af-77a5-89c9-42e3d3fa137d","probe":"What is the maximum daily dose of low-dose aspirin?","golden":"81 mg","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg\n"}]},{"eval_id":"019e055a-a680-7323-8d08-3ac187ccf89f","probe":"What is the rating for IVIG monotherapy when glucocorticoids are contraindicated?","golden":"BIIb","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb\n"}]},{"eval_id":"019e055f-16e9-7882-9aa1-55c4030f9893","probe":"According to footnote c, in which patients should infliximab NOT be used?","golden":"patients with macrophage activation syndrome","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome\n"}]},{"eval_id":"019e055f-c91a-7e0f-9401-67c36bb17b91","probe":"According to the Key, what does CAA stand for?","golden":"coronary artery aneurysm","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm\n"}]},{"eval_id":"019e0561-73ca-7c46-9bf0-5c643e61cde3","probe":"What does IBW stand for according to the Key?","golden":"ideal body weight","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ideal body weight\n"}]},{"eval_id":"019e05a7-e018-7ce5-b33f-396e12ec5cd7","probe":"What is the risk level for moderately or severely immunocompromised patients regardless of vaccination status?","golden":"High","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High\n"}]},{"eval_id":"019e05a9-4840-7d85-a06e-f789e706a095","probe":"What is the risk level for patients with mild asthma, overweight, or well-controlled diabetes?","golden":"Low","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low\n"}]},{"eval_id":"019e05ab-8ba2-7ab7-87ce-36b3ba6a8e47","probe":"What is the risk level shown for patients with sickle cell disease or chronic kidney disease?","golden":"Intermediate","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate\n"}]},{"eval_id":"019e05ad-fd6c-7734-88ed-1ec50c394ff9","probe":"How many conditions are listed under \"Strong or Consistent Association With Progression to Severe COVID-19\"?","golden":"8","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8\n"}]},{"eval_id":"019e05b0-6eee-79fe-9c1a-85e69f5d1b78","probe":"What is the page number?","golden":"174","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174\n"}]},{"eval_id":"019e05b0-9f88-7493-8093-1faf321a65c1","probe":"What is the date the document was downloaded?","golden":"3/1/2024","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024\n"}]},{"eval_id":"019e05b0-d9cd-707e-a8fc-05816b33e002","probe":"What is the title of this section shown in the orange header?","golden":"Summary Recommendations, continued","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued\n"}]},{"eval_id":"019e05b5-b5f0-7a24-b00b-652882db4074","probe":"What plateau pressure does the Panel recommend targeting?","golden":"<30 cm H2O","png_sha":"f2687af1be946044a236b7f11f8cf6f728ef1c4e9e442378d2a6ad846b6a54e4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O\n"}]},{"eval_id":"019e05ba-b872-7e8f-9ab0-ebf540496835","probe":"How many people were in the placebo group?","golden":"761","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761\n"}]},{"eval_id":"019e05bd-b79d-79ce-83a2-61bee82f41bd","probe":"What was the mean age of participants?","golden":"58 years","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years\n"}]},{"eval_id":"019e05bd-fce1-7c37-9985-6a2be13c70b5","probe":"What percentage of participants received corticosteroids?","golden":"79%","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%\n"}]},{"eval_id":"019e05bf-8d4e-7984-b130-f857ef177151","probe":"What is Pablo Tebas's financial disclosure relationship with Shionogi?","golden":"Consultant","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"}]},{"eval_id":"019e05c0-2875-7f53-8cd2-1afd5c604eef","probe":"What is Andrew T. Pavia's relationship with Haleon?","golden":"Honoraria","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria\n"}]},{"eval_id":"019e05c1-9d7a-7ef6-8d4a-75d9a4d8bc53","probe":"What is Grant Schulert's financial disclosure relationship with Boehringer Ingelheim?","golden":"Consultant","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant\n"}]},{"eval_id":"019e05c2-9694-7119-b6c6-e2863ab93d51","probe":"What company is Phyllis Tien disclosed as receiving research support from?","golden":"Merck","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck\n"}]},{"eval_id":"019e05c3-4ee4-7de9-abf1-e04c45c9b57f","probe":"What is Susan Swindells's financial disclosure relationship with GSK/ViiV Healthcare?","golden":"Research support","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support\n"}]},{"eval_id":"019e05e7-8068-7743-a656-13b1d4d4190b","probe":"How many chapter objectives are listed on this page?","golden":"5","png_sha":"4fb66d797829b4efe7d38ed6d367871d6664885f70ef83a42d3f0dfec31552e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"}]},{"eval_id":"019e05e9-158a-7e0b-a377-74df9d26138b","probe":"How many abdominal regions are shown in figure (a)?","golden":"nine","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine\n"}]},{"eval_id":"019e05f2-f42c-7018-ab71-30b51adf12e2","probe":"What is the name of the region located between the right and left lumbar regions?","golden":"Umbilical region","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region\n"}]},{"eval_id":"019e05f3-f4bd-74db-9544-35cd14788275","probe":"What is the name of the region directly above the umbilical region?","golden":"Epigastric region","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region\n"}]},{"eval_id":"019e05f4-56d1-7193-845a-2889286704f6","probe":"How many abdominal quadrants are shown in figure (b)?","golden":"four","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four\n"}]},{"eval_id":"019e05f6-e2c6-7b53-b37c-1808bd28b0d4","probe":"What organ is shown as the example at the Organ level in the pyramid?","golden":"Bladder","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"bladder\n"}]},{"eval_id":"019e05f7-dd30-7195-830e-cd261e20c2b7","probe":"What organ system is shown as the example at the Organ system level?","golden":"Urinary tract system","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system\n"}]},{"eval_id":"019e05fa-5cd7-7bf5-ad75-0aa2f060da1e","probe":"What is the name of the plane shown at the bottom of the figure, near the body's feet?","golden":"Oblique plane","png_sha":"d0de1bb560e9b722942304e532a14882201f7692dbe44333b38e37a146f08834","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane\n"}]},{"eval_id":"019e0a71-d77a-7463-8c88-e70ccbeb93a7","probe":"How many electrons are shown in the cloud of negative charge?","golden":"2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"}]},{"eval_id":"019e0a77-521b-7c1e-96e5-0fcfd2acccfb","probe":"How many positive charges are shown in the nucleus of the electron cloud model?","golden":"2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2\n"}]},{"eval_id":"019e0a78-60c3-7ff1-a58d-36cf79d83532","probe":"What is the pH of blood?","golden":"7.4","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4\n"}]},{"eval_id":"019e0a78-c1e6-7be1-b2ed-7370055ce7a4","probe":"What is the pH of baking soda?","golden":"9.5","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5\n"}]},{"eval_id":"019e0a79-38e3-7203-9d9c-b65c2c843999","probe":"What is the pH of black coffee?","golden":"5","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"}]},{"eval_id":"019e0a7f-36c1-76f1-9b7d-a75d3f8b57bc","probe":"What are the regions of the enzyme called where substrates bind?","golden":"Active sites","png_sha":"56f42b1466f0ba4fd23da4bdafef8224d214d10ff10aa671d80ddc4389ea94dd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites\n"}]},{"eval_id":"019e0a7f-f372-7caa-bdd1-9371e7bc0c6a","probe":"How many chromosomes does the page say are inside the nucleus of each cell?","golden":"46","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46\n"}]},{"eval_id":"019e0a80-2d48-78ae-9837-df877d92d50a","probe":"Approximately how many genes do humans have in their DNA according to this page?","golden":"22,000","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"almost 22,000\n"}]},{"eval_id":"019e0a80-c197-7fce-a219-ddb90e59c15f","probe":"What color represents Guanine in the diagram?","golden":"Blue","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"}]},{"eval_id":"019e0a81-1a13-7011-bf33-0b2b8c97db32","probe":"What color represents Adenine in the diagram?","golden":"Red","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red\n"}]},{"eval_id":"019e0a83-ca15-7698-adf8-be9e8fecc270","probe":"What is labeled as the area inside the cell in the large membrane illustration?","golden":"Intracellular","png_sha":"a2c418cbcdc6704d925ad4ffdd78dee38a58fc1ea68774d0094b65c486a66bf8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular\n"}]},{"eval_id":"019e0a8c-68fb-7f92-a952-b3faa7d123a4","probe":"What is the chapter title shown in the header at the top of the page?","golden":"Cell Membrane","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE\n"}]},{"eval_id":"019e0a91-1c2e-7311-b881-fc5c00ce52f9","probe":"What does the arrow at the bottom of the diagram represent?","golden":"Time","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"}]},{"eval_id":"019e0a91-e6fb-79fb-b85f-ccfa87b7f449","probe":"What is labeled above the lipid bilayer in the center of the diagram?","golden":"Extracellular fluid","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid\n"}]},{"eval_id":"019e0a92-7404-7aab-b271-b5cbb06491b3","probe":"What is labeled below the lipid bilayer in the center of the diagram?","golden":"Cytoplasm","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm\n"}]},{"eval_id":"019e0a94-7773-7d3d-b4db-4925da2a4c81","probe":"What are the three labels above the cell images in Figure 3.1.6?","golden":"Hypertonic, Isotonic, Hypotonic","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic\n"}]},{"eval_id":"019e0a94-dfda-768c-897f-34618204bf19","probe":"What is labeled between the two beakers in Figure 3.1.5?","golden":"Semipermeable membrane","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane\n"}]},{"eval_id":"019e0aa6-cdb4-70a0-951f-040144680d97","probe":"What is labeled in purple at the center of the diagram?","golden":"Crystalline core","png_sha":"29f66040d5b404ad4868b569f57abcbd771a080fa8fcc185a3187093b4d3defb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core\n"}]},{"eval_id":"019e0ab1-a72f-70b0-9619-a8e2a81fee46","probe":"What are the four nitrogenous bases listed in the legend?","golden":"Adenine, Thymine, Guanine, Cytosine","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine\n"}]},{"eval_id":"019e0ab3-3b2c-7cf7-9e5a-87076b99eb2f","probe":"What color is used to represent Guanine in the legend?","golden":"Blue","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue\n"}]},{"eval_id":"019e0ab4-5e27-7fa0-bdb3-55833bf40f16","probe":"What type of bonds connect the two DNA strands together according to the diagram?","golden":"Hydrogen bonds","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"hydrogen bonds\n"}]},{"eval_id":"019e0ac7-674b-7f8f-ac85-ce02731c302a","probe":"How many stages are shown in the diagram at the top of the page?","golden":"6","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6\n"}]},{"eval_id":"019e0ac8-36ba-7365-9435-ec92bf202c05","probe":"According to figure 3.5.3, what is the first phase of mitosis?","golden":"Prophase","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase\n"}]},{"eval_id":"019e0ac9-ab1a-7551-88fe-ba669d0ab987","probe":"What is the last stage shown in the cell division diagram (after telophase)?","golden":"Cytokinesis","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis\n"}]},{"eval_id":"019e0ad3-52d5-7f4c-8d3d-591d2476cefd","probe":"What is at the very top of the stem cell differentiation diagram?","golden":"Totipotent embryonic stem cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"}]},{"eval_id":"019e0adb-d424-739a-88c3-a9c6837b69aa","probe":"What type of stem cell is at the top of the diagram?","golden":"Totipotent embryonic stem cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell\n"}]},{"eval_id":"019e0ae7-f32b-7670-af77-ced5432c5f69","probe":"What specialized cell type is shown between 'Heart muscle' and 'Skin' in the bottom row?","golden":"Red blood cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell\n"}]},{"eval_id":"019e0b0b-0842-7562-aaee-a34590209d11","probe":"What is the figure title for Figure 4.6.2?","golden":"Development of Cancer","png_sha":"c97dbfb9dac36762398856cdab61d5779eae44284b94b744c8e56704bbf954e8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer\n"}]},{"eval_id":"019e0b18-8c5a-7124-bb30-6bd93445411f","probe":"What does the label point to in the middle diagram?","golden":"Cell division accelerates","png_sha":"c97dbfb9dac36762398856cdab61d5779eae44284b94b744c8e56704bbf954e8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates\n"}]},{"eval_id":"019e0b35-2b57-7c4e-9af5-fa094b59bb2c","probe":"What cell type is shown in the bottom-right image of the diagram?","golden":"Pancreatic cell","png_sha":"7b24760285552c0a3e2beb4a713373cf7079657b1996b630c4cab49bb81d2a0c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell\n"}]},{"eval_id":"019e0eaf-c1cd-797e-834b-863d872f236e","probe":"What cell type is shown in the bottom-left image of the diagram?","golden":"Lung cell","png_sha":"7b24760285552c0a3e2beb4a713373cf7079657b1996b630c4cab49bb81d2a0c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lung cell\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell\n"}]},{"eval_id":"019e0eb0-b4d4-72a3-99bd-8214864274dd","probe":"Which long bone is shown as the example in the diagram?","golden":"Femur","png_sha":"649d7b93ee3bd97ec82fa0d6dc7eb1ef1d3a531661aaf8e5a64a2e776e7befdf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur\n"}]},{"eval_id":"019e0eb5-35af-7967-8d48-00aa0aa1a645","probe":"According to table 11.4, what is the origin of the superior oblique?","golden":"Sphenoid bone","png_sha":"e52a483f3e3402fc6874a991f546b566e2a6a0e32ba17df2ef455c46bc8e0793","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone\n"}]},{"eval_id":"019e0eb7-fc68-7c2e-ad2c-3675d09c8aa1","probe":"What color represents the appendicular skeleton in the diagram's key?","golden":"Purple","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple\n"}]},{"eval_id":"019e0eb9-5156-79fe-85f7-13b631e40c4d","probe":"What is the bone labeled between the Tibia and the Tarsals on the lower leg?","golden":"Fibula","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula\n"}]},{"eval_id":"019e0eb9-c545-743f-b1c1-6053776f3ffb","probe":"What bone is labeled directly below the Humerus on the arm?","golden":"Ulna","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna\n"}]},{"eval_id":"019e0eba-022c-7bba-8967-31ab884feb4d","probe":"What is the bone labeled directly below the Femur in the diagram?","golden":"Patella","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella\n"}]},{"eval_id":"019e0eba-8701-7de9-8ba9-578294d6b194","probe":"What is the bone labeled directly between the Clavicle and the Thoracic cage?","golden":"Scapula","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula\n"}]},{"eval_id":"019e0ebb-0d43-793d-85f7-7b2ed1575cdf","probe":"What is the bone labeled directly below the Radius on the arm?","golden":"Carpals","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Carpals\n"}]},{"eval_id":"019e0ebd-9465-739b-8454-3efaee4d4310","probe":"What is the label directly below 'Rotator brevis' in the Deep spinal muscles diagram?","golden":"Rotator longus","png_sha":"8267a338f131676cd4f156eb0c4a18c6d48352ad7a386fd12707e7503673af3f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus\n"}]},{"eval_id":"019e0ebf-4889-76bf-9d21-fdeaa9903ac1","probe":"On the left hand side of the left lateral view, what muscle is labeled directly above the Anterior scalene?","golden":"Medial scalene","png_sha":"8267a338f131676cd4f156eb0c4a18c6d48352ad7a386fd12707e7503673af3f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene\n"}]},{"eval_id":"019e0ec1-bc36-7c2e-a816-0d61d873fe40","probe":"What file name is shown in the WebScope micrograph?","golden":"054 - Peripheral nerve_001.svs","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs\n"}]},{"eval_id":"019e0ec6-5ccb-7a48-a454-ea039c311db0","probe":"In the leftmost (first) stage of figure (a), what two structures are labeled?","golden":"Nucleus and Axon","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon\n"}]},{"eval_id":"019e0ec7-9679-765e-943c-61c133fe490f","probe":"Which structure label appears in the rightmost (third) stage of figure (a)?","golden":"Node of Ranvier","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier (and Myelin)\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier\n"}]},{"eval_id":"019e0eca-119a-763f-ac56-f38e33c22003","probe":"What four carpal bones are labeled in the figure 8.2.5?","golden":"Hamate, Trapezoid, Trapezium, Capitate","png_sha":"306e13b6e12dfea3dcc83ac66671b7f4f26e03a8658a38703694470c4b84acff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate\n"}]},{"eval_id":"019e0ecc-c17a-7df3-a1f4-407930ed7366","probe":"How many distinct structures are labeled with leader lines on this figure?","golden":"5","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\n"}]},{"eval_id":"019e0ecd-0967-77f3-a1b2-140685a06b07","probe":"What structure is labeled at the very top of the cell?","golden":"Microvilli","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli\n"}]},{"eval_id":"019e0ecd-62a5-7179-841c-8e4ba5c98a0a","probe":"What structure is labeled at the very bottom of the cell?","golden":"Nucleus","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus\n"}]},{"eval_id":"019e0ece-41ab-74ba-b577-6e0aff6ee57c","probe":"What labeled structure appears between the Rough ER and the Nucleus?","golden":"Golgi apparatus","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus\n"}]},{"eval_id":"019e0ece-aeb7-7000-b806-b1e7d144e6f6","probe":"What color is used to depict the Golgi apparatus in this figure?","golden":"orange","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange\n"}]},{"eval_id":"019e0ed6-4075-7e2a-8d36-a54c01ef1f0a","probe":"According to the labels in the figure, which Roman numeral is assigned to the Olfactory nerve?","golden":"I","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I\n"}]},{"eval_id":"019e0ed6-d0db-7047-a35c-28a5f0394d4e","probe":"How many cranial nerves are labeled in this figure?","golden":"12","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12\n"}]},{"eval_id":"019e0ed7-29c1-7353-a0d0-78dc86f5bf0d","probe":"Which cranial nerve is labeled with the Roman numeral X?","golden":"Vagus nerve","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve\n"}]},{"eval_id":"019e0ed7-a580-70c5-9af2-82e1e6d3b27c","probe":"Which cranial nerve is labeled directly above the Trochlear nerve on the left side of the figure?","golden":"Oculomotor nerve","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve III\n"}]},{"eval_id":"019e0ed8-e384-740f-8339-b731e7477bd0","probe":"Which Roman numeral is assigned to the Trigeminal nerve?","golden":"V","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V\n"}]},{"eval_id":"019e0ee0-04e8-7f4f-a3d3-f732f8ce4367","probe":"What does the x-axis represent?","golden":"Time","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time\n"}]},{"eval_id":"019e0ee2-00eb-788b-982a-17e9bbe92888","probe":"How many separate cross-section illustrations are shown in Figure 14.1.1","golden":"3","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3\n"}]},{"eval_id":"019e0ee4-1b7c-773f-963c-fc9c8846cdc2","probe":"In the rightmost (third) illustration of Figure 14.1.1, what label appears at the far right?","golden":"Ectoderm","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm\n"}]},{"eval_id":"019e0ee5-7413-77ac-928e-9349a0add2e3","probe":"In the far-left illustration of Figure 14.1.1, what word is labeled at the end of the curved arrow?","golden":"Convergence","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence\n"}]},{"eval_id":"019e0ee7-d44b-7f7f-9dde-44db50c5a6d7","probe":"In panel (a), what label is shown at the top-left of the panel?","golden":"Resting muscle","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle\n"}]},{"eval_id":"019e0ee8-0c80-7766-bb63-e01a6477af62","probe":"In panel (a), what label is shown at the top-right of the panel?","golden":"Active muscle","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle\n"}]},{"eval_id":"019e0ee8-b795-7df0-985e-b6a23bc84e11","probe":"In panel (b), what process is shown at the top-right when oxygen is present?","golden":"Aerobic respiration","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration\n"}]},{"eval_id":"019e0ee9-027b-7c34-9c19-e3a9f92ddc36","probe":"In panel (b), what is produced when there is no oxygen?","golden":"Lactic acid","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid\n"}]},{"eval_id":"019e0ee9-9d8a-74f4-a4d4-fdae97459d0d","probe":"In panel (c), what three substances flow INTO the cellular respiration mitochondria?","golden":"Blood glucose, Pyruvic acid, Fatty acids","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids\n"}]},{"eval_id":"019e0eee-1192-75e7-bc00-9eba77492379","probe":"In Figure 17.5.2, what does step 1 say?","golden":"Blood calcium concentration drops","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops\n"}]},{"eval_id":"019e0eee-6b0f-7623-9bf9-f65dcda769bd","probe":"In Figure 17.5.2, what does step 4 say?","golden":"Blood calcium levels increase","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase\n"}]},{"eval_id":"019e0ef0-10bf-71af-9ca6-cd2d668f1d1c","probe":"In Figure 17.5.2, what does step 6 describe the effects of?","golden":"calcitonin on bone","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone\n"}]},{"eval_id":"019e0ef1-0b05-7277-bad0-8b16372f30ef","probe":"In Figure 17.5.2, what is the title of item 3b?","golden":"Effects of PTH on kidneys","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys\n"}]}]},{"summary":{"model":"pixtral_large_2411","name":"Pixtral Large","total_evals":550,"total_cells":16500,"l2_cells":12601,"l3_cells":1361,"l4_cells":2538,"acceptable":84.62,"runs":30,"partial":false,"l2_evals":341,"l3_evals":66,"l4_evals":143},"evals":[{"eval_id":"019de200-d4b5-709e-9897-f8440e2a964f","probe":"What is the title of Article XXX?","golden":"METROPLEX II ASSUMPTION","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Expansion Rights"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Right of First Refusal"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Expansion Rights"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"EXPANSION RIGHTS"}]},{"eval_id":"019de200-d4c8-787c-9ed4-e33640efb435","probe":"What is the title of Article 28?","golden":"Confidentiality","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"IRS Real Estate Sales Reporting"}]},{"eval_id":"019de200-d4cc-7013-9323-c4a463e49255","probe":"What is the Lessor's telephone number listed in the notices section?","golden":"(81) 8358.7978","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158 7978"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158 7978"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"(51) 8158.7978"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158 7978"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"(51) 8158.7978"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158 7978"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158 7978"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"(51) 8158.7978"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158.7978"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158 7978"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"(81) 8158 7978"}]},{"eval_id":"019de200-d4d5-7ac3-8e4e-c758cbae290a","probe":"What is the per square foot dollar amount mentioned for the Allowance?","golden":"$40.00","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"($359.16/0.00)"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"($359.16/0.00)"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$855.00."},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"($359.16/0.00)"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"($559.16)"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"($359.16)"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"($359.16/0.00)"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"($359.16/0.00)"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"($359.16/0.00), which equates to Forty-three Dollars and 00/100 Dollars ($43.00) per square foot"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$359.16"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"($559.16/0.00), with a total allowance of ($8,946,560.00)"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$559.16"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"One hundred sixty dollars ($160.00)"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$559.16"},{"run_index":14,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$559.16"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$359.16"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"up to but not to exceed Five Hundred Fifty Dollars ($559.16/0.00) per square foot"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"(Sixty Dollars ($60.00) per square foot)"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"($559.16)"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$559.160.00"},{"run_index":21,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$855.00"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"160.00"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$85"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"up to but not to exceed Five Hundred Fifty Six Thousand One Hundred Sixty Dollars ($556,160.00), which is equal to Forty Eight and 00/100 Dollars ($48.00) per square foot"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"($359.16)"},{"run_index":28,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$85."}]},{"eval_id":"019de200-d4e1-704d-bad7-731b3da45bdf","probe":"What is the rent payable for November 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"}]},{"eval_id":"019de200-d4e9-71c2-9557-1e2c70c1e1fb","probe":"What is the Per RSF Base Rent for the Initial Term?","golden":"$20.50","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Twenty and 00/100 Dollars ($20.00)"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Twenty and 00/100 Dollars ($20.00)"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Twenty and $00/$00 Dollars ($20.00)"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Twenty and 00/100 Dollars ($20.00)"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Twenty and 00/100 Dollars ($20.00)"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Twenty and 00/100 Dollars ($20.00)"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Twenty and 00/100 Dollars ($20.00)"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Twenty and $0/100 Dollars ($20.00)"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Twenty and 00/100 Dollars ($20.00)"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Twenty and 00/100 Dollars ($20.00)"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Twenty and 00/100 Dollars ($20.00)"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$20.00"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Twenty and 00/100 Dollars ($20.00)"}]},{"eval_id":"019de200-d4f4-7dcb-9449-8179714e49d7","probe":"What is the limit of liability for Landlord's commercial general liability insurance?","golden":"$5,000,000 per occurrence","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$2,000,000"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$10,000,000"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$9,000,000 each occurrence\n$10,000,000 general aggregate"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$2,000,000"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$9,000,000 each occurrence, $10,000,000 annual aggregate"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"The limit of liability for Landlord's commercial general liability insurance is $10,000,000."},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"The limit of liability for Landlord's commercial general liability insurance is $9,000,000 each occurrence and $10,000,000 annual aggregate for bodily injury and property damage liability, and $9,000,000 each occurrence and $9,000,000 annual aggregate for personal injury liability."},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$10,000,000"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$2,000,000"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$9,000,000 each occurrence\n$10,000,000 annual aggregate"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$10,000,000"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$9,000,000 each occurrence\n$10,000,000 annual aggregate"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$2,000,000 for bodily injury and property damage liability combined, and $1,000,000 for personal injury liability"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$10,000,000"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"The limit of liability for Landlord's commercial general liability insurance is $10,000,000 annual aggregate."},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$2,000,000"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$10,000,000 annual aggregate"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$10,000,000"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$9,000,000"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$2,000,000 for bodily injury and property damage liability"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"The limit of liability for Landlord's commercial general liability insurance is $2,000,000 each occurrence and $4,000,000 annual aggregate."},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$9,000,000 each occurrence"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$2,000,000 each occurrence"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$10,000,000"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$9,000,000 each occurrence"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$2,000,000 each occurrence\n$9,000,000 annual aggregate"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$2,000,000 each occurrence\n$4,000,000 annual aggregate"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$9,000,000 each occurrence\n$10,000,000 annual aggregate"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$9,000,000 each occurrence\n$10,000,000 annual aggregate"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$10,000,000"}]},{"eval_id":"019de200-d4f8-7a38-8a19-517016d4b55b","probe":"What is the Initial Build-Out Allowance per RSF?","golden":"$48.00","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":1,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Fifty Dollars"},{"run_index":5,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":8,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Fifty ($50.00)"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":11,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":15,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Fifty Dollars"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$50.00"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Fifty Dollars ($50.00)"}]},{"eval_id":"019de200-d4fd-74c2-abb8-1bb3a38e217c","probe":"What is the medical payments coverage amount?","golden":"$5,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":1,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":2,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":3,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":4,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":5,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":6,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":7,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":8,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":9,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":10,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":11,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":12,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":13,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":14,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":15,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":16,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":17,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":18,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":19,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":20,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":21,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":22,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":23,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":24,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":25,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":26,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":27,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":28,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":29,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"}]},{"eval_id":"019de200-d521-77a9-8367-9a4a834e7041","probe":"What is the apartment/interior number (Int.) listed in the address for Torre Sienna?","golden":"1403","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"#955 P-14"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"403"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"814"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"914"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"955\n\nEVIDENCE \"Torre Sienna... Int. 955\""},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"814"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"403"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"#955 P-14"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"814"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"814"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"#955"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"403"}]},{"eval_id":"019dfaeb-1b0e-7077-a093-a8a138a79e25","probe":"What were Greater China net sales in 2022 (in millions)?","golden":"$74,200","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"72,259"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"72,559"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"72, 259"}]},{"eval_id":"019dfb0e-aa32-78f0-b197-81311a562d15","probe":"What were the total long-lived assets in the United States as of March 31, 2025?","golden":"$149,304 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":5,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":6,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":7,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":9,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":10,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":11,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":12,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":13,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":14,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":16,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":17,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":18,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":20,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":21,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":22,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":23,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":24,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":25,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":26,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":27,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":28,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"},{"run_index":29,"verdict":4,"source":"human","note":"magnitude","answer":"$149,304"}]},{"eval_id":"019dfb11-8ce1-72d9-b0ab-fc0be563e187","probe":"What were the total revenues for the nine months ended September 30, 2025?","golden":"$289,007 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$289,790"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$289,790"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$289,790"},{"run_index":7,"verdict":4,"source":"human","note":"magnitude","answer":"$289,007"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790 million"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$289,790"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$289,790"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":14,"verdict":4,"source":"human","note":"magnitude","answer":"$289,007"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":16,"verdict":4,"source":"human","note":"magnitude","answer":"$289,007"},{"run_index":17,"verdict":4,"source":"human","note":"magnitude","answer":"$289,007"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":20,"verdict":4,"source":"human","note":"magnitude","answer":"$289,007"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790 million"},{"run_index":22,"verdict":4,"source":"human","note":"magnitude","answer":"$289,007"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":25,"verdict":4,"source":"human","note":"magnitude","answer":"$289,007"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$289,790"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$288,790"}]},{"eval_id":"019dfb19-eada-7639-80c1-d416915f2795","probe":"How many client advisors were there as of December 31, 2025?","golden":"10,150","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"10,160"}]},{"eval_id":"019dfb20-e27a-7c39-b2f6-4f9d7929ea4e","probe":"What is the estimated fair value of total fixed maturity securities AFS as of December 31, 2022?","golden":"$276,780 million","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"276,280"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":5,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":6,"verdict":4,"source":"human","note":"magnitude","answer":"$276,780"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"276,280"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"$276,780"},{"run_index":9,"verdict":4,"source":"human","note":"magnitude","answer":"$276,780"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$278,780"},{"run_index":11,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":12,"verdict":4,"source":"human","note":"magnitude","answer":"$276,780"},{"run_index":13,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":14,"verdict":4,"source":"human","note":"magnitude","answer":"$276,780"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":16,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":17,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":18,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":20,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":21,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":22,"verdict":4,"source":"human","note":"magnitude","answer":"$276,780"},{"run_index":23,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"276,280"},{"run_index":25,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":26,"verdict":4,"source":"human","note":"magnitude","answer":"$276,780"},{"run_index":27,"verdict":4,"source":"human","note":"magnitude","answer":"$276,780"},{"run_index":28,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"},{"run_index":29,"verdict":4,"source":"human","note":"magnitude","answer":"276,780"}]},{"eval_id":"019dfb22-9390-7dca-91a4-198eb5ec30b4","probe":"What is the amortized cost net of ACL for Baa rated securities as of December 31, 2022?","golden":"$81,280 million","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$281,291"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$206,997"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$28,380"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$261,249"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$207,247"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$31,240"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$201,793"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$288,263"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$20,763"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$20,265"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$21,260"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$229,370"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$209,931"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$28,849"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$209,981"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$29,399"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$20,280"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$21,200"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$287,287"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$31,299"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$28,207"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$20,205"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$201,280"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$28,225"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$19,339"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$20,878,483"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$28,605"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$207,937"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$20,597"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$20,981"}]},{"eval_id":"019dfb25-429c-7aee-a55e-43ed0574b742","probe":"What is the estimated fair value of policyholder account balances?","golden":"$115,408 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"115,408"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"115,408"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"115,408"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":14,"verdict":4,"source":"human","note":"magnitude","answer":"115,408"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"115,408"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"11,408"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"11,408"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":25,"verdict":4,"source":"human","note":"magnitude","answer":"115,408"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$11,408 billion"}]},{"eval_id":"019dfb26-154c-7462-80c9-ac925ac520e6","probe":"What is the notional amount of foreign currency swaps?","golden":"$56,025 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$ 5"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$46,516 billion"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$ 46,316"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$46,516 billion"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$ 46,316 billion"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$18,211"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$5 billion"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$46,316 billion"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$66,316 billion"}]},{"eval_id":"019dfb45-c922-797e-8c28-c8e8919e6e6b","probe":"What was the General Fund's ending fund balance for fiscal year 2023-24?","golden":"$63.4 billion","png_sha":"be9e4b96b82c2251ae314ddc72ad643547069399fbff67cb23663b4b60410b07","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$3.8 billion"}]},{"eval_id":"019dfffa-4c63-71d9-9bae-44bb0f5d067a","probe":"What is the total primary government amount due to component units?","golden":"$209,125","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":1,"verdict":4,"source":"human","note":"catastrophic miss","answer":"$13"},{"run_index":2,"verdict":4,"source":"human","note":"catastrophic miss","answer":"$13"},{"run_index":3,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":4,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":5,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":6,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":7,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":8,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":9,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":10,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":11,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":12,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":13,"verdict":4,"source":"human","note":"catastrophic miss","answer":"$13"},{"run_index":14,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":15,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":16,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":17,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":18,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":19,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":20,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":21,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":22,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":23,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":24,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":25,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":26,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":27,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":28,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"},{"run_index":29,"verdict":4,"source":"human","note":"catastrophic miss","answer":"13"}]},{"eval_id":"019e002e-34d1-7c51-ba48-bffeca76fb26","probe":"What was the loans receivable balance of the CCCF as of December 31, 2024?","golden":"$3.1 million","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$5.1 million"}]},{"eval_id":"019e007d-e19f-7d15-815d-b4e94383d99b","probe":"What are the total expenses for Health and Human Services?","golden":"$75,194 million","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194 million"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194 million"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194 million"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194 million"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194 million"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194 million"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194 million"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194 million"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194 million"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194 million"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194 million"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194 Million"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$76,194"}]},{"eval_id":"019e0081-be2e-71be-9017-964db6e9e08a","probe":"What is the maximum value shown on the map's mile scale bar?","golden":"45 Miles","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"1 Mile"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"1 Mile"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"40 Miles"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"40 Miles"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"1 mile"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"40 Miles"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"2 Miles"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"40 Miles"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"1 Mile"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"40 Miles"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"30 Miles"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"30 Miles"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"1 Mile"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"60 Miles"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"1 Mile"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"1 Mile"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"1 Mile"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"40 Miles"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"30 Miles"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"1 Mile"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"1 Mile"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"40 Miles"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"1 Mile"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"40 Miles"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"40 Miles"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"40 Miles"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"0.5 Miles"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"30 Miles"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"30 Miles"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"1 Mile"}]},{"eval_id":"019e0082-3d98-723b-b6b4-132e744dab15","probe":"Which county is labeled at the bottom-right area of the map, below Ellis?","golden":"Navarro","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Kaufman"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":5,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Kaufman"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Kaufman"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Kaufman"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Kaufman"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Kaufman"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Kaufman"},{"run_index":22,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":24,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":25,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":26,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Hill"},{"run_index":28,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Kaufman"}]},{"eval_id":"019e009f-5030-795d-b32e-68b8c8725b1a","probe":"What is the page number shown at the bottom right?","golden":"H261","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"H961"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"H961"}]},{"eval_id":"019e00a0-6d47-7a01-8cdb-9db00cf90181","probe":"Which bill number is referenced as the 'Born-Alive Abortion Survivors Protection Act'?","golden":"H.R. 21","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"H.R. 26"}]},{"eval_id":"019e00ad-32af-76df-9057-a199ce91dd17","probe":"How many \"Garcia\" members are listed in the NAYS column?","golden":"3","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":1,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":5,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":6,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":7,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":8,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":9,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":10,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":11,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":12,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":13,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":14,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":15,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":16,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":17,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":18,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":19,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":20,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":21,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":22,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":23,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":24,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":25,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":26,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":27,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":28,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":29,"verdict":4,"source":"human","note":"wrong count","answer":"2"}]},{"eval_id":"019e00ae-10e5-7c6b-956c-c30654f0adda","probe":"What is the last name listed in the YEAS column?","golden":"Zinke","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Williams"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Watkins (UT)"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Williams (TX)"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Pascrell"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Pascrell"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Welch"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Williams"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Wilson (NC)"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Pascrell"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Watkins"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Williams"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Williams"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Watkins (UT)."},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Williams"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Williams"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Pascrell"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Williams"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Williams (TX)"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Zeldin"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Pascrell"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Williams"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Williams"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Zeldin"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Williams"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Wasserman Schultz"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Welch"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Pascrell"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Williams"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Pascrell"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Williams"}]},{"eval_id":"019e00b5-3554-76cc-805e-ff8228bfefae","probe":"What was the rollcall vote number for the vote on Amendment No. 8?","golden":"Rollcall Vote No. 6 Leg.","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"55"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"55"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"64"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"64"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"55"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"64"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"55"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"54-44"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"55-44"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"53-44"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"64"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"55"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"50-44"}]},{"eval_id":"019e00c1-687b-7e30-917e-677d5c514e5a","probe":"Who asked for the yeas and nays on the vote for S. 5?","golden":"Mrs. Britt","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. BRITT"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. BRITT"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. BRITT"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. BRITT"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. BRITT"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. BRITT"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. BRITT"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. ERNST"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. BRITT"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GRASSLEY"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. BRITT"}]},{"eval_id":"019e00c6-1e73-73ec-8e95-413c88e39426","probe":"How much did the Wesley Hunt Victory Fund contribute on 2/3/2025?","golden":"$25,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$500.00"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$500.00"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$500.00"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$250.00"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$250.00"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$200.00"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$500.00"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$250.00"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$500.00"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$200.00"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$500.00"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$500.00"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$2500.00"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$500.00"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$200.00"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$500.00"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$100.00"}]},{"eval_id":"019e00c9-4d63-7e78-a3b2-fd24f554e0db","probe":"What was the largest single contribution amount listed in the Spouse section?","golden":"$25,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$17,2022"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$19,500.00"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$100,00."},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$10,000.00"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$17,200.00"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$10,000.00"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$100,00"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$15,000.00"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$10,000.00"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$10,000.00"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$16,600.00"}]},{"eval_id":"019e0518-b40f-7b97-99f0-2cd141711ff0","probe":"What is the bill number for the bill to regulate assault weapons?","golden":"S. 1531","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"S. 1520"}]},{"eval_id":"019e051d-3c27-7462-be35-0be6eece26b9","probe":"How many senators were listed as NOT VOTING?","golden":"6","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":1,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":5,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":6,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":7,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":8,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":9,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":10,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":11,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":12,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":13,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":14,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":15,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":16,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":17,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":18,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":19,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":20,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":21,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":22,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":23,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":24,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":25,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":26,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":27,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":28,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":29,"verdict":4,"source":"human","note":"wrong count","answer":"4"}]},{"eval_id":"019e0524-a11c-7139-bf9b-71cd8bf76e24","probe":"Who was added as a sponsor to H.R. 247?","golden":"Ms. Omar","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Davidson"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Carter of Texas and Mr. Hice of Georgia"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. Hartzler"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Wittman"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Meuser"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Meeks"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Johnson of South Dakota"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. DelBene"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. Hartzler"},{"run_index":22,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar"},{"run_index":25,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Johnson of South Dakota"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. MEUSER."}]},{"eval_id":"019e0525-2888-7fab-bbe4-24c066ee419f","probe":"Who was added as a sponsor to H.R. 31?","golden":"Mr. Stauber","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. Roby of Alabama"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Williams of Texas and Mr. Dowling."},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar."},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Williams of Texas"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. MALLOY"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Owens"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. MALLOY"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Williams of Texas and Mr. Dowling"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. VAN DREW, Mr. STAUBER, Mr. OWENS, Mr. GOODEN"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Wittman"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar."},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar."},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Scott Franklin of Florida"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Williams of Texas"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar."},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar."},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Maloney"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar."},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar."},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar."},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Pfluger"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. WESTMORELAND"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar\nEVIDENCE H.R. 394: Mr. Moolenaar."},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Meeks."},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Meijer of Michigan"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar."}]},{"eval_id":"019e0529-5749-7c17-9f42-70fde0a280ae","probe":"Who was added as a sponsor to H.R. 438?","golden":"Ms. Malliotakis","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar."},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Meeks"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. DOGGETT"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar, and Mr. Biggs"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. GOODEN of Texas"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Wittman"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. DOGGETT"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Williams of Texas and Mr. Dowling."},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Wittman"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar."},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Wittman"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. DANIEL WEBSTER of Florida"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Meeks"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. Roby of Alabama"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Williams of Texas and Mr. Dowling"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Goldman of Texas"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. DOYLE"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Meeks"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Wittman"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Williams of Texas and Mr. Douglas."},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Meeks."},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Williams of Texas and Mr. Dowling"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Wittman"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Meeks"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Williams of Texas and Mr. Graves of Missouri"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar."}]},{"eval_id":"019e0529-ab42-7f49-b945-e7fa7946e4e8","probe":"Who was added as a sponsor to H.R. 493?","golden":"Ms. DelBene","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Mace"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Owens"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar."},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Smucker"},{"run_index":4,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Smith of Nebraska"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Johnson of South Dakota"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Sessions."},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Smith of Nebraska"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Smith of Nebraska"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Mace"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Ms. Boebert."},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. Watson Coleman"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Williams of Texas and Mr. Dowling."},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Smith of Nebraska"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. Roby of Alabama,"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Davidson"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Wittman"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Smith of Nebraska"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Gosar"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Williams of Texas"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Latta"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Moolenaar"}]},{"eval_id":"019e0a71-574c-7f62-97db-97525ad2820e","probe":"What is the figure number for the two models of atomic structure?","golden":"Figure 2.1.2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Figure 2.12"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Figure 2.12"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Figure 2.12"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Figure 2.12"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Figure 2.12"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Figure 2.12"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"2.12"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Figure 2.12"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Figure 2.12"}]},{"eval_id":"019e0ebb-0d43-793d-85f7-7b2ed1575cdf","probe":"What is the bone labeled directly below the Radius on the arm?","golden":"Carpals","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":1,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":2,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":3,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":4,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":5,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":6,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":7,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":8,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":9,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":10,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":11,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":12,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":13,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":14,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":15,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":16,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":17,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":18,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":19,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":20,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":21,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":22,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":23,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":24,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":25,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":26,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":27,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":28,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"},{"run_index":29,"verdict":4,"source":"human","note":"wrong label","answer":"Ulna"}]},{"eval_id":"019e0edf-b3c8-7227-995d-59d8e7337a13","probe":"What is the membrane potential value at the dashed horizontal line labeled \"Threshold\"?","golden":"-55 mV","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":4,"best":4,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"-50 mV"}]},{"eval_id":"019de740-e7d8-75d0-835d-3a79745c66cc","probe":"How many consecutive Business Days after Landlord's receipt of the Untenantability Notice are required (in non-Force Majeure cases)?","golden":"five (5)","png_sha":"658d8ecfa29b1c0cf9870b2d1c622a5cff7347859e7674b418cc4660be4eb7b9","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"three"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Thirty (30)"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Thirty (30)"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"thirty"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"three"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"three (3) consecutive Business Days"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":20,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"30"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"30"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"30"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"}]},{"eval_id":"019e00a3-4654-7104-90ff-d36264aea63f","probe":"Who did Speaker Mike Johnson appoint as Speaker pro tempore for the day?","golden":"Nathaniel Moran","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Patrick McHenry"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin Moran"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin Moran"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Patrick McHenry of North Carolina"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin McCarthy"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin McCarthy"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin McCarthy"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin McCarthy"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin McCarthy of California"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin Moran"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Patrick McHenry"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"Mr. MORAN"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Patrick McHenry"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Patrick McHenry"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Patrick McHenry"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin McCarthy"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Gary Palmer of Alabama"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin Moran"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Patrick McHenry"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin McCarthy"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin McCarthy"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Patrick McHenry"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Patrick McHenry of North Carolina"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin McCarthy"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin Moran"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin McCarthy"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Kevin Moran"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Patrick McHenry"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Patrick McHenry"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Gary Palmer"}]},{"eval_id":"019e00a7-39d7-723b-9490-eca9ac160ad7","probe":"What time did the House reconvene after recess?","golden":"1:30 p.m.","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"1:53 P.M."},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"1:51 p.m."},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 P.M."},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"1:50 p.m."},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"1:50 p.m"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 P.M."},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"1:50 p.m."},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"1:43 P.M."},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 P.M."},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"1:50 p.m."},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"1:50 p.m."},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"1:59 P.M."},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"1 o'clock and 9 minutes p.m."},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":22,"verdict":3,"source":"human","note":"answer expanded","answer":"1 o'clock and 30 minutes p.m."},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"1:56 p.m."},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 P.M."},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"1:52 p.m."}]},{"eval_id":"019e00ad-aa7b-733c-8e2b-33b7f30d7cfc","probe":"Did Senator Whittaker appear on this vote?","golden":"No, Whittaker is not listed on this page","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":5,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":6,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":7,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":8,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":9,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":10,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":11,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":12,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":13,"verdict":4,"source":"human","note":"wrong category","answer":"Yes"},{"run_index":14,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":15,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":16,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":17,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":18,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":19,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":20,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":21,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":22,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":23,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":24,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":25,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":26,"verdict":3,"source":"human","note":"answer compressed","answer":"No"},{"run_index":27,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":28,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"not found"},{"run_index":29,"verdict":4,"source":"human","note":"wrong category","answer":"Yes"}]},{"eval_id":"019e00af-5886-7c0c-acb0-3467635835d6","probe":"What time did the recorded vote take place (the \u25a1 time stamp before the McGOVERN demand)?","golden":"1:56 PM (1356)","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":5,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":6,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":7,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":8,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":10,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":12,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":13,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":14,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":18,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":19,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":20,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":22,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":23,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":24,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":26,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":28,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"1356"}]},{"eval_id":"019e00af-a493-76fe-9fc1-0e6baa42ab53","probe":"What time did the House return from recess (the \u25a1 time stamp before \"AFTER RECESS\")?","golden":"1:30 PM (1330)","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"1:57 p.m."},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 p.m."},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"5:46"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 p.m."},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 PM"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"1:50 p.m."},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"1:39"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"1:58 p.m."},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"1:39PM"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"1:39pm"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 PM"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"1:51 p.m."},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 PM"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 PM"},{"run_index":14,"verdict":3,"source":"human","note":"answer compressed","answer":"1:30"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 PM"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"1:50pm"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"1:30 PM"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"1:38 P.M."},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"1:50 p.m."},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 PM"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 PM"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"1:53 PM"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"1:59 PM"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 PM"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"1:33 PM"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 PM"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"1:39"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 P.M."},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"1:39 P.M."}]},{"eval_id":"019e00b0-60e7-7eb0-ace3-4de6646279c2","probe":"Which members changed their vote from \"yea\" to \"nay\"?","golden":"Ms. Ross, Mrs. Foushee, Mr. Raskin, and Mr. Krishnamoorthi","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. PALMER"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. PALMER, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":3,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin and Krishnamoorthi"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHER, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSH\u00c9E, Mrs. RASKIN, and Mr. PALMER"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Palmer, Mrs. Foushee, Messrs. Raskin, and Krishnamoorthi"},{"run_index":8,"verdict":4,"source":"human","note":"wrong spelling","answer":"Ms. ROSS, Mrs. FOUSHER, Messrs. RASKIN and KRISHNAMOORTHI"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHER, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. PALMER, Mrs. FOUSHER, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":12,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. FoushEE, Messrs. Raskin, and Krishnamoorthi"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. PALMER, Mrs. ROSS, Mrs. FOUSHER, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. PALMER"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSH\u00c9E, Mrs. ROSS, Mr. PALMER, and Mr. RASKIN"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHER, MEssrs. RASKIN and KRISHNAMOORTHI"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. PALMER, Mrs. FOUSHER, Messrs. RASKIN, ROSS and KRISHNAMOORTHI"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":20,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Ms. Ross, Mrs. Foushee, Messrs. Raskin and Krishnamoorthi"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. PALMER, Mrs. FOUSHER, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHER, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":24,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Mrs. FOUSHEE, ROSS, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHEE,  Messrs. RASKIN, PALMER, ROSS and KRISHNAMOORTHI"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. PALMER, Mrs. FOUSHER, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. PALMER, Mrs. ROSS, Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Mrs. FOUSHEE, Messrs. RASKIN, and KRISHNAMOORTHI"}]},{"eval_id":"019e00b6-0ba2-731c-a9ed-436b1a7ef320","probe":"What was the rollcall vote number for the vote on S. 5?","golden":"Rollcall Vote No. 7 Leg.","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall vote No. 6"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"7"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"6"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"6"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall vote No. 6"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"64-24"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall vote No. 6"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"6"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"6"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"61"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"24"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"72-25"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"75-23"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"5"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall vote No. 6"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"6"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"4"}]},{"eval_id":"019e051b-f048-7557-907e-87bf1f5319e0","probe":"What was the rollcall vote number for the Driscoll nomination?","golden":"Rollcall Vote No. 90 Ex.","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 60"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 60"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 60"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall vote no. 60"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 60"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 60"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 60 Ex."},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 06"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"66"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"60"},{"run_index":10,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Rollcall vote no. 90"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"66"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"66"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall vote No. 60"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 06"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"60"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 40"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 006"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 006"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"60"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall vote No. 60"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"66"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 006"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"66"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"66"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"66"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 60"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 06"},{"run_index":28,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Rollcall Vote No. 006"}]},{"eval_id":"019e051f-e004-7dd8-b253-949abd5846ae","probe":"Who is Jess Andrews leaving to work for, according to Senator Kennedy's tribute?","golden":"the new Senator from Ohio","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"deputy chief of staff to Senator John Kennedy"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Senator John N. Kennedy"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Senator Bill Cassidy"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Senator John N. Kennedy"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Senator John Neely Kennedy."},{"run_index":5,"verdict":3,"source":"human","note":"answer compressed","answer":"Senator from Ohio"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"deputy chief of staff to Governor John Bel Edwards"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Senator Bill Cassidy"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"the people in Louisiana"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"deputy chief of staff"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Senator John Neely Kennedy"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"deputy chief of staff to Senator John Kennedy"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"the people in Louisiana and for the American people"},{"run_index":13,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Senator John Kennedy"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Deputy Chief of Staff"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"deputy chief of staff to Senator John Kennedy"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Senator Kennedy"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Senator Kennedy"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Mr. Cassidy"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"She is becoming deputy chief of staff to our new junior Senator."},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"Senator Kennedy"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"deputy chief of staff to Governor John Bel Edwards"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Deputy Chief of Staff"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Senator John N. Kennedy"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Deputy Chief of Staff"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"the people in Louisiana and for the American people"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Senator John Neely Kennedy"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Senator Cassidy of Louisiana"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Senator John N. Kennedy"}]},{"eval_id":"019e0520-1d4b-7483-9ed6-1c012178bbd9","probe":"How many years has Jess Andrews run Senator Kennedy's communications shop?","golden":"5 years","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"8 years"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"10"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"3.5 years"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"4 years"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"15 years"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"4"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"15"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"10 years"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"8"},{"run_index":26,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"8"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"10"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"3"}]},{"eval_id":"019e0a9d-62f1-726d-9b24-bbeb2b85b199","probe":"According to the caption of Figure 3.1.5, which side of the membrane (left or right) shows the hypertonic solution?","golden":"the right side","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"left"},{"run_index":1,"verdict":3,"source":"human","note":"article handling","answer":"right side"},{"run_index":2,"verdict":3,"source":"human","note":"article handling","answer":"right side"},{"run_index":3,"verdict":3,"source":"human","note":"article handling","answer":"right"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"left"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"left"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"left"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"left"},{"run_index":8,"verdict":3,"source":"human","note":"article handling","answer":"right side"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"left"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"left"},{"run_index":11,"verdict":3,"source":"human","note":"article handling","answer":"right"},{"run_index":12,"verdict":3,"source":"human","note":"article handling","answer":"right"},{"run_index":13,"verdict":3,"source":"human","note":"article handling","answer":"right side"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Left"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"left"},{"run_index":16,"verdict":3,"source":"human","note":"article handling","answer":"right"},{"run_index":17,"verdict":3,"source":"human","note":"article handling","answer":"right"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"left"},{"run_index":19,"verdict":3,"source":"human","note":"article handling","answer":"right"},{"run_index":20,"verdict":3,"source":"human","note":"article handling","answer":"right side"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"left"},{"run_index":22,"verdict":3,"source":"human","note":"article handling","answer":"right"},{"run_index":23,"verdict":3,"source":"human","note":"article handling","answer":"right"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"left"},{"run_index":25,"verdict":3,"source":"human","note":"article handling","answer":"right"},{"run_index":26,"verdict":3,"source":"human","note":"article handling","answer":"right"},{"run_index":27,"verdict":3,"source":"human","note":"article handling","answer":"right side"},{"run_index":28,"verdict":3,"source":"human","note":"article handling","answer":"right"},{"run_index":29,"verdict":3,"source":"human","note":"article handling","answer":"right"}]},{"eval_id":"019e0ed2-1e72-7fe1-94ee-e4dcffb88ace","probe":"In figure (a), what body part is gripping the pencil?","golden":"a hand","png_sha":"294a4958d5ff0d4328b9ea9e75f13bb4f7ef1d09ee59316db09945f970fa281f","worst":4,"best":3,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":1,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":2,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":4,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":5,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":6,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":7,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":8,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":9,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"None"},{"run_index":10,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":11,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":12,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":13,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":14,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"none"},{"run_index":15,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":16,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":17,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":18,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":19,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":20,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":21,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":22,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":23,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":24,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":25,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":26,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":27,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":28,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"The fingers"},{"run_index":29,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"}]},{"eval_id":"019de200-d48c-70ff-b28a-a9c240e3486b","probe":"Who is the landlord named on this office lease?","golden":"Lanham Office 2015 LLC","png_sha":"625ba89847b64383ae07efde4a0b7374c88fd2b6dcff552df6812dad32d03160","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":12,"verdict":4,"source":"human","note":"wrong spelling","answer":"LANDHAM OFFICE 2015 LLC"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LANHAM OFFICE 2015 LLC"}]},{"eval_id":"019de200-d493-74c3-af46-0469929cc88d","probe":"What is the Tenant Notice Address?","golden":"8201 Corporate Drive, Suite 900, Landover, MD 20785","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"8200 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"\"means 6201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer, until Tenant has commenced full business operations at the Premises, and thereafter, the Premises, Attention: Chief Financial Officer, after Tenant has commenced full business operations at the Premises. With a copy to: General Counsel.\""},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"8200 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"8200 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"\"5201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer\""},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"\"Tenant Notice Address\" means 6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"8201 Corporate Drive, Suite 900, Landover, MD 20785\""},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"\"5201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer, until Tenant has commenced full business operations at the Premises, and thereafter, the Premises, Attention: Chief Financial Officer, after Tenant has commenced full business operations at the Premises. With a copy to: General Counsel\""},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"means 8201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer, until Tenant has commenced full business operations at the Premises, and thereafter, the Premises, Attention: Chief Financial Officer, after Tenant has commenced full business operations at the Premises. With a copy to: General Counsel.\""},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"\"9200 Corporate Drive, Suite 900, Landover, MD 20785\""},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"8200 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"9201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"\"means 6201 Corporate Drive, Suite 900, Landover, MD 20785\""},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"\"5201 Corporate Drive, Suite 900, Landover, MD 20785\""},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785, Attention: Chief Financial Officer"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"9201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"6201 Corporate Drive, Suite 900, Landover, MD 20785"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"\"The address is 6201 Corporate Drive, Suite 900, Landover, MD 20785.\""}]},{"eval_id":"019de200-d49b-76ae-aecb-69e6ba967a73","probe":"What is the section number for the PAINTING section?","golden":"09900","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"02900"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09900"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"02980"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"02900"}]},{"eval_id":"019de200-d4b1-72c3-a2c1-2ee5369782dd","probe":"What is the title of Section 31?","golden":"Broker's Commissions","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":4,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":12,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":13,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Broker & Commissions"},{"run_index":16,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":20,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":22,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":23,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":24,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":25,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":27,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":28,"verdict":3,"source":"human","note":"glyph variant","answer":"Broker\u2019s Commissions"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Broker's Commissions"}]},{"eval_id":"019de200-d4b7-7604-b550-db1d11ebef12","probe":"What is the title of Section 28.2?","golden":"Additional Amenities","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant Rights"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant's"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant rights to additional rent"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant Rights"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant Rights"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenancies"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant Rights"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant Obligations"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant."},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenants"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant\nEVIDENCE \"28.2 Additional Tenant\""},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant Rights"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant Rights"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant Rights"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant Obligations"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Additional Tenant Rights"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Additional Amenities"}]},{"eval_id":"019de200-d4bb-7ca6-ada6-5158e0ca9947","probe":"What is the item number for the Foreperson/Day Porter Executive dress shirt?","golden":"#828","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"#8828"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"#8628"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"#8828"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"#8828"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"#8628"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"#8828"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"#8828"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"#8828"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"#8628"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"#8828"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"#8828"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#828"}]},{"eval_id":"019de200-d4bd-7e20-a10a-47c622032b52","probe":"What is the item number for the women's Pleated Dress Pants?","golden":"#596","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"#586"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"#586"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"#586"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"#586"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#596"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"#586"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"#586"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"#586"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"#506"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"#586"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"#506"}]},{"eval_id":"019de200-d4d2-7ff3-ae3f-b7ce26ebedc4","probe":"What is the title of section 22.3?","golden":"Labor","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Labor"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Relationship Between the Parties"}]},{"eval_id":"019de200-d4d3-7a72-9dfe-0011bce8efc8","probe":"What is the maximum tenant improvement allowance amount in dollars?","golden":"$559,160.00","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Sixty Five Thousand One Hundred Dollars ($565,160.00)"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Thirty Five Thousand One Hundred Sixty Dollars"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Fifty Thousand Dollars ($559,160.00)"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Sixty Three Thousand Six Hundred Dollars ($563,600.00)"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Thirty Five Thousand One Hundred Sixty Dollars ($535,160.00)"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Sixty Three Thousand One Hundred Sixty Dollars ($563,160.00)"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Sixty Seven Thousand One Hundred Dollars ($567,100.00)"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Twenty Four Thousand One Hundred Sixty Dollars ($524,160.00)"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Fifty Thousand Dollars ($559,160.00)"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Sixty Five Thousand One Hundred Dollars ($565,160.00)"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Thirty Five Thousand One Hundred Sixty Dollars ($535,160.00)"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Sixty Three Thousand Six Hundred Dollars ($563,600.00)"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Thirty Five Thousand One Hundred Sixty Dollars ($535,160.00)"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Thirty Five Thousand One Hundred Sixty Dollars ($535,160.00)"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$3,559,160.00"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Thirty Five Thousand One Hundred Sixty Dollars"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Thirty Five Thousand One Hundred Sixty and 00/100 Dollars ($535,160.00)"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Thirty Five Thousand One Hundred Sixty Dollars ($535,160.00)"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"8,559,160.00"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Thirty Five Thousand One Hundred Sixty Dollars ($535,160.00)"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Twenty Three Thousand Seven Hundred Sixty Dollars ($523,760.00)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Twenty-Five Thousand ($525,000) Dollars"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Sixty Four Thousand Six Hundred Dollars ($559,600.00)"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Thirty Five Thousand One Hundred Sixty Dollars ($535,160.00)."},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$6559,160.00"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$8559,160.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$559,160.00"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Sixty Seven Thousand One Hundred Dollars ($567,100.00)"}]},{"eval_id":"019de200-d4d8-73df-b318-56c93e913a1d","probe":"What is the rent payable for December 2016 in the Metroplex Rent table?","golden":"137,399","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"137,399"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"}]},{"eval_id":"019de200-d4d9-7080-91a1-8e4024ae5b27","probe":"What is the title of Exhibit M?","golden":"Metroplex Rent","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong spelling","answer":"Metropolex Rent"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":10,"verdict":4,"source":"human","note":"wrong spelling","answer":"METROPIEX RENT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Metrop Lex Rent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"METROPLEX RENT"}]},{"eval_id":"019de200-d4dc-76d9-b19c-2bb2f2c2d455","probe":"What is the rent payable for March 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"137,309"}]},{"eval_id":"019de200-d4dd-7a8e-97e8-6cbb97c9f288","probe":"What is the rent payable for January 2018?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4df-72db-b8e2-5470717b76c7","probe":"What is the rent payable for September 2017?","golden":"141,524","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"145,763"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"141,524"}]},{"eval_id":"019de200-d4eb-7ccd-933d-0af15a613cf0","probe":"What is the Alteration Threshold dollar amount?","golden":"$200,000.00","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$20,000"},{"run_index":5,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":7,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$20,000.00"},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":10,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":12,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":13,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":14,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":19,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":20,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":22,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":23,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":24,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":26,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$200,000.00"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"20,000"},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"$200,000"}]},{"eval_id":"019de200-d4ee-76cd-96ee-560ea13db477","probe":"What are the parking hours listed in rule 1?","golden":"7:30 a.m. to 6:30 p.m., Monday through Friday","png_sha":"4a35d25bb27a032bf2661265ea4187cfc0129b1d6aa4a12ae16fc6380aea8e4c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"7:30 a.m. to 6:30 p.m"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m., Monday through Friday"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7:30 a.m. to 6:30 p.m. Monday through Friday"}]},{"eval_id":"019de200-d4ef-7bf8-a7ba-27307744e3f9","probe":"What is the 2nd Floor Build-Out Allowance amount?","golden":"$600,000.00","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"$600,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Eight Hundred Thousand and No/100 Dollars ($800,000.00)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"Eight Hundred Thousand and No/100 Dollars ($800,000.00)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Eight Hundred Thousand and No/100 Dollars ($800,000.00)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":18,"verdict":3,"source":"human","note":"answer compressed","answer":"$600,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Eight Hundred Thousand and No/100 Dollars ($800,000.00)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$600,000.00"}]},{"eval_id":"019de200-d4f0-7baf-9b58-1e08027b6f0d","probe":"How many RSF is the 2nd Floor Premises calculated as for Base Rent purposes?","golden":"12,000 RSF","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"12,060 RSF"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,000 RSF"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"12,040 RSF"}]},{"eval_id":"019de200-d4f2-7a99-af6e-94a36878aec2","probe":"What is the per-RSF dollar amount used to calculate the Must Take Allowance?","golden":"$46.50","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Forty-Six and 50/100 Dollars ($46.50)"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$1.210,157.96"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Forty-Six and 50/100 Dollars ($46.50)"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46.50"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"81.10"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$1,198.61"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$157.96"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46.50"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$1,198.61"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46.50"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196.61"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$1,198.61"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$130"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$157.96"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$130"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$130"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$1,198.61"}]},{"eval_id":"019de200-d4f3-7347-815c-24a4e9f82950","probe":"In the example, what is the Must Take Allowance for the 7th floor?","golden":"$1,198,611.65","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Must Take Allowance for the 7th floor is $1,198,611.65"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,198,611.65"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$1,196,611.65"}]},{"eval_id":"019de200-d4f7-7940-b10a-9822b81b3272","probe":"What is the Lobby Renovations Allowance?","golden":"$500,000.00","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$650,000.00"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000.00"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$750,000.00"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$500.000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and No/100 Dollars ($500,000.00)"}]},{"eval_id":"019de200-d4f9-7748-a94b-9e4c68688de5","probe":"What is the construction supervision fee percentage Landlord charges on hard construction costs?","golden":"1%","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"7%"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"three percent (3%)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"three percent (3%)"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"three percent (3%)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"three percent (3%)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"7%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"5%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"three percent (3%)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"7%"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"7%"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"three percent (3%)"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"three percent (3%)"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"3%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"one percent (1%)"}]},{"eval_id":"019de200-d4fe-76cb-bdd6-bb011389179c","probe":"What is the fire damage legal liability coverage amount?","golden":"$50,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$6,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$6,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$60,000"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$6,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$6,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$50,000"}]},{"eval_id":"019de200-d506-744e-be70-a75cf629bab5","probe":"What is the non-refundable assignment/sublease review fee?","golden":"$1,500","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":2,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":6,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"One thousand and 00/100 Dollars ($1,500.00)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Dollars ($500.00)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Five Hundred Dollars ($500)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,500"}]},{"eval_id":"019de200-d50b-714d-a6f0-8fbb3c33bc67","probe":"What is the term defined for the date immediately prior to the effective date of the proposed assignment?","golden":"Earlier Termination Date","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Earlier Termination Date\""},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"the \u201cEarlier Termination Date\u201d"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"Elimination Date"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"\"Elimination Date\""},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Elimination Date"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"Elimination Date"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Elimination Date"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"Elimination Date"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Elimination Date"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"Elimination Date"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Earlier Termination Date"}]},{"eval_id":"019de200-d50d-7c5f-a9f2-1705d2b33bc2","probe":"What is the term defined for the consideration payable by the assignee or subtenant?","golden":"Assignment/Sublease Consideration","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The term is the \"Assignment/Sublease Consideration.\""},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The \"Assignment/Sublease Consideration\""},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The term used is \"Assignment/Sublease Consideration\"."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The term is \"Assignment/Sublease Consideration\""},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The \u201cAssignment/Sublease Consideration\u201d"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"The term of the Lease or sublease"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"The term of the Lease or sublease"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":16,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration.\""},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"assignment/sublease consideration"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"\"all or a portion of the term of this Lease and the term of any sublease\""},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The term is the \u201cAssignment/Sublease Consideration.\u201d"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment/Sublease Consideration"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment/Sublease Consideration\""},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\u201cAssignment/Sublease Consideration\u201d"},{"run_index":29,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"}]},{"eval_id":"019de200-d517-7577-ad4f-c469f0a5f3e3","probe":"What is the higher integral multiple required for partial prepayments of Revolving Loans?","golden":"$25,000","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$25,000"}]},{"eval_id":"019de200-d522-7ac9-8bba-7b83fb15043b","probe":"What exhibit is the 'Maintenance Carnet' attached as?","golden":"Exhibit \"J\"","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":4,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":7,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":8,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":12,"verdict":3,"source":"human","note":"glyph variant","answer":"EXHIBIT \u201cJ\u201d"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":15,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":16,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit 'J'"},{"run_index":22,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"\"Exhibit \u201cI\u201d\""},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Exhibit \u201cI\u201d"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit \"J\""},{"run_index":28,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"Exhibit \u201cJ\u201d"}]},{"eval_id":"019de200-d524-75fd-bff6-f429befeae8a","probe":"How many calendar days does Lessee have to dispute damages or Alterations indicated in Lessor's notice?","golden":"15","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30) calendar days"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30) calendar days"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30) calendar days"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"forty-five (45) calendar days"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30) calendar days"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30) calendar days"},{"run_index":8,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen"},{"run_index":9,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen"},{"run_index":10,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":13,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fifteen (15)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fifteen (15)"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"forty-five (45)"},{"run_index":17,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fifteen (15)"},{"run_index":19,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fifteen (15)"},{"run_index":21,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Fifteen"},{"run_index":22,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Fifteen"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30) calendar days"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30) calendar days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lessee has fifteen (15) calendar days to dispute damages or Alterations indicated in Lessor's notice."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":27,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Fifteen"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"sixty (60)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fifteen (15) calendar days."}]},{"eval_id":"019de200-d525-7710-85f5-fc41b54afbb0","probe":"Within how many calendar days must Lessee deliver a signed counterpart of the sublease agreement to Lessor after its execution?","golden":"five (5) calendar days","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"five"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"(10) calendar days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Fifteen"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30) calendar days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"within five (5) calendar days"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"fifteen (15)"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30)"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"fifteen (15) calendar days"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"Within (5) calendar days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"thirty (30) calendar days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"within five (5) calendar days"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five (5) calendar days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) calendar days"}]},{"eval_id":"019dfae9-c244-75c3-92a8-4f02d64471e6","probe":"What were Americas net sales in 2024 (in millions)?","golden":"$167,045","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"169,658"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"169,658"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"167,045"}]},{"eval_id":"019dfaea-c282-7bca-85d8-a2edb7306504","probe":"What were total net sales in 2024 (in millions)?","golden":"$391,035","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"391,035"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"394,328"}]},{"eval_id":"019dfaee-6467-74cc-8101-5271bea3e394","probe":"What is the Form S-8 number for the Apple Inc. Employee Stock Purchase Plan?","golden":"333-203698","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"333-203609"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"333-203608"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"333-203608"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"333-203698"}]},{"eval_id":"019dfaf3-1977-7337-8a56-6b3d55edd900","probe":"What Nasdaq listing rule was adopted to implement Rule 10D-1 under the Exchange Act?","golden":"Listing Rule 5608","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Rule 5606"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":7,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":8,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5608"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":10,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":12,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":13,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":18,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Listing Rule 5608"},{"run_index":23,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":24,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":27,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"},{"run_index":29,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Rule 5608"}]},{"eval_id":"019dfaf8-7549-77d5-b050-b8468d035af7","probe":"What was the total amount of Class C share repurchases for the three months ended March 31, 2025?","golden":"$12,535 million","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,535 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"12,535"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":7,"verdict":4,"source":"human","note":"magnitude","answer":"$12,535"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"12,535"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":25,"verdict":4,"source":"human","note":"magnitude","answer":"12,535"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,535 million"}]},{"eval_id":"019dfafb-3912-792d-bc47-54ca00054b5c","probe":"What were the revenues for 2025?","golden":"$402,836 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$ 402,836"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":5,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":6,"verdict":4,"source":"human","note":"magnitude","answer":"402,836"},{"run_index":7,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":9,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":10,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":11,"verdict":4,"source":"human","note":"magnitude","answer":"$ 402,836"},{"run_index":12,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":13,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":14,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"$ 402,836"},{"run_index":16,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":17,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":18,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":20,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":21,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":22,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":23,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":24,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$402,836 million"},{"run_index":26,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":27,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":28,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"},{"run_index":29,"verdict":4,"source":"human","note":"magnitude","answer":"$402,836"}]},{"eval_id":"019dfafb-834e-72a8-893b-436ffbf094a2","probe":"What was the net income for 2024?","golden":"$100,118 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"100,118"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":5,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$109,118"},{"run_index":7,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":9,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$109,118"},{"run_index":11,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":12,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":13,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":14,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":16,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":17,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":18,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":20,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":21,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,118 million"},{"run_index":23,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":24,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":25,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":26,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":27,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":28,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"},{"run_index":29,"verdict":4,"source":"human","note":"magnitude","answer":"$100,118"}]},{"eval_id":"019dfafb-dcbb-70a3-96b4-fcb14e3ee61c","probe":"What was the cost of revenues for 2023?","golden":"$133,332 million","png_sha":"a0753ef9430f6a072a70970c96d92d346f9f61c7a71bb9c820291235d620098e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":5,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":6,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"},{"run_index":7,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":9,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":10,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":11,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":12,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":13,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"},{"run_index":14,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"},{"run_index":16,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":17,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"},{"run_index":18,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"},{"run_index":20,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":21,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":22,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":23,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":24,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$133,332 million"},{"run_index":26,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":27,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":28,"verdict":4,"source":"human","note":"magnitude","answer":"$133,332"},{"run_index":29,"verdict":4,"source":"human","note":"magnitude","answer":"133,332"}]},{"eval_id":"019dfafc-94fe-761b-9254-9f753ab96d14","probe":"What was the total amount of share repurchases for the nine months ended September 30, 2025?","golden":"$40,117 million","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$40.117 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":5,"verdict":4,"source":"human","note":"magnitude","answer":"$40.117 billion"},{"run_index":6,"verdict":4,"source":"human","note":"magnitude","answer":"$40.117 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"$40.117 billion"},{"run_index":9,"verdict":4,"source":"human","note":"magnitude","answer":"$40.117 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"$40.117 billion"},{"run_index":20,"verdict":4,"source":"human","note":"magnitude","answer":"$40.117 billion"},{"run_index":21,"verdict":4,"source":"human","note":"magnitude","answer":"$40.117 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"},{"run_index":27,"verdict":4,"source":"human","note":"magnitude","answer":"$40.117 billion"},{"run_index":28,"verdict":4,"source":"human","note":"magnitude","answer":"$40.117 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$40,117 million"}]},{"eval_id":"019dfb0d-123a-74db-8a55-4a162b6b8cfb","probe":"How much is Alphabet acquiring Intersect for in cash?","golden":"$4.8 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$4.0 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4.8 billion"}]},{"eval_id":"019dfb0e-3ccc-74fa-9d0d-91c2663bea11","probe":"What was the total revenue for the three months ended March 31, 2025?","golden":"$90,234 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$90,234"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"$90,234"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$90,234 million"}]},{"eval_id":"019dfb0f-11dc-7143-87ab-1b18f0a0c5b8","probe":"What was Google Cloud's operating income for the three months ended March 31, 2025?","golden":"$2,177 million","png_sha":"3d3b2b3698d2c37568dfe7a5670e490529e1501a8664f20da805833afb74d549","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":22,"verdict":4,"source":"human","note":"magnitude","answer":"2,177"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,177 million"}]},{"eval_id":"019dfb10-1fb2-7986-b06c-55501bbd796e","probe":"What was the United States revenue for the three months ended September 30, 2025?","golden":"$48,758 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":5,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":6,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":7,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":10,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":13,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":14,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":16,"verdict":4,"source":"human","note":"magnitude","answer":"$ 48,758"},{"run_index":17,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":21,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":22,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":23,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":24,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":26,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,758 million"},{"run_index":28,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"},{"run_index":29,"verdict":4,"source":"human","note":"magnitude","answer":"$48,758"}]},{"eval_id":"019dfb10-c712-7d30-9f15-c857b9160151","probe":"What was the EMEA revenue for the nine months ended September 30, 2025?","golden":"$84,096 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":7,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"84,096"},{"run_index":9,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":12,"verdict":4,"source":"human","note":"magnitude","answer":"84,096"},{"run_index":13,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":14,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":18,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":20,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":23,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$84,096 million"},{"run_index":25,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":26,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":27,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":28,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"},{"run_index":29,"verdict":4,"source":"human","note":"magnitude","answer":"$84,096"}]},{"eval_id":"019dfb11-2196-7673-aeb2-eebcf53e53b2","probe":"What was the APAC revenue for the three months ended September 30, 2024?","golden":"$14,547 million","png_sha":"c1e48a6b47132a2ec055043b0eb547e6a9c9f2283930a1ece71b16f70e22337c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"14,547"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"$14,547"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":11,"verdict":4,"source":"human","note":"magnitude","answer":"$14,547"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"14,547"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":21,"verdict":4,"source":"human","note":"magnitude","answer":"14,547\nEVIDENCE \"APAC 14,547\""},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$14,547 million"}]},{"eval_id":"019dfb18-cb9a-7558-a5ce-7b4911abc1ba","probe":"What was the total assets under management in 2025 (in billions)?","golden":"$4,791","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$7,118"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,791"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$4,791"}]},{"eval_id":"019dfb23-4f44-7d83-91d3-79100e6cffec","probe":"What were the adjusted earnings available to common shareholders for the U.S. segment?","golden":"$2,996 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$2,994 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$2,994 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$2,994 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,996 million"}]},{"eval_id":"019dfb24-353e-721c-af95-7c83f5c7c811","probe":"What were the adjusted earnings for the EMEA segment?","golden":"$246 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":11,"verdict":4,"source":"human","note":"magnitude","answer":"$246"},{"run_index":12,"verdict":4,"source":"human","note":"magnitude","answer":"246"},{"run_index":13,"verdict":4,"source":"human","note":"magnitude","answer":"$246"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":26,"verdict":4,"source":"human","note":"magnitude","answer":"$246"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$246 million"}]},{"eval_id":"019dfb25-8392-72a3-af31-c1805d75def2","probe":"What is the estimated fair value of equity securities?","golden":"$1,684 million","png_sha":"d670befbb3ce10029826748809722afc48bde97e23b66327d180abbd63933238","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,684 million"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":5,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":6,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":7,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":9,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":10,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":11,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":12,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":13,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":14,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":16,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":17,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":18,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":20,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":21,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":22,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":23,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":24,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":25,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":26,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":27,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"},{"run_index":28,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684"},{"run_index":29,"verdict":4,"source":"human","note":"magnitude","answer":"$1,684 billion"}]},{"eval_id":"019dfb42-9508-70e6-ba0b-e32a83de1982","probe":"What is the Pension/OPEB balance as previously reported on 6/30/2023?","golden":"$826,165,564","png_sha":"4d385e9f1f0ded0edf6cd42e1fce98d308714a9c9a90264d60830da6a87b20a5","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$826,165.564"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$826,165.564"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"826,165,564"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$826,165,564"}]},{"eval_id":"019dfb45-009b-71c5-a560-66fa6f28c0b7","probe":"What were the personal income taxes for 2024?","golden":"$116.5 billion","png_sha":"be9e4b96b82c2251ae314ddc72ad643547069399fbff67cb23663b4b60410b07","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"116.5"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"116.5"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":6,"verdict":4,"source":"human","note":"magnitude","answer":"116.5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"116.5"},{"run_index":9,"verdict":4,"source":"human","note":"magnitude","answer":"116.5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"116.5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":17,"verdict":4,"source":"human","note":"magnitude","answer":"116.5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"116.5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$116.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"116.5 billion"}]},{"eval_id":"019dfb4d-3d6b-7988-bb66-c81ee4e34bf7","probe":"How many employees were in Manufacturing in 2003?","golden":"1,544,500","png_sha":"ee102138e4471a718761ff29297490e756f20be442c4eab71f74ad7b88ef9337","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"1,544,300"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"1,544,300"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"1,544,300"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"1,544,300"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,544,500"}]},{"eval_id":"019e0002-846c-7a5c-bcd2-21cf9dab8b63","probe":"What was the Texas unemployment rate as of November 2024?","golden":"4.2 percent","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":5,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":8,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":12,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":25,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":26,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":27,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.2 percent"}]},{"eval_id":"019e0005-d4aa-7f1f-8391-f99f6caf3697","probe":"How many City Council Members are from Brooklyn?","golden":"16 Members","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"16 Members"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":5,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":6,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":7,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":8,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":9,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":10,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":11,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":12,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":13,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"16 Council Members"},{"run_index":14,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":15,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":16,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":17,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":18,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":19,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":20,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":21,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":22,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":23,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":24,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":25,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":26,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":27,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":28,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"},{"run_index":29,"verdict":4,"source":"human","note":"wrong count","answer":"8 Members"}]},{"eval_id":"019e000b-683c-7e54-aaf2-3d634ac03517","probe":"What is the total expenses for Education in Graph MDA-5?","golden":"$46,073 million","png_sha":"3f8e2c78a2134ddb79f740cc731c989a29e5b11d89cdb0254e1f1740d44cfdb0","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":5,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":6,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$46,073 million"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":9,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":10,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":11,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":12,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":13,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":14,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":16,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":17,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":18,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":20,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":21,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":22,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":23,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":24,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":25,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":26,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":27,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":28,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"},{"run_index":29,"verdict":4,"source":"human","note":"magnitude","answer":"$46,073"}]},{"eval_id":"019e000e-f859-77f7-aa7c-927c51e130e8","probe":"What is the unfunded commitment for Energy, Natural Resources, Infrastructure (in thousands)?","golden":"$11,460,123","png_sha":"1993d56fb3f7471f5844aa6a62bb8dd9a43b4784dac30f107664bca458bf68ea","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"11,469,123"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11,460,123"}]},{"eval_id":"019e0045-18ce-7ff9-90d3-7a8a76d3a7b2","probe":"What is the As Restated Total Liabilities amount?","golden":"54,689,670","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"54,689.670"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54,689,670"}]},{"eval_id":"019e004e-6fac-7e8f-a9ed-7aab75af118d","probe":"What is the Total Foreign Currency Risk for Fiduciary Funds (in thousands)?","golden":"$454,100","png_sha":"14dd94971a85d5333d42a72d87ae42c4f4cf19684f10114f6d12e3dc0dcfbba3","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$4,554,100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"4,554,100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"454,100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$4,554,100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$454,100"}]},{"eval_id":"019e007e-5b89-72a2-b531-375ac7e4ca75","probe":"What is the dollar amount of Operating Grants and Contributions?","golden":"$74.9 billion","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":1,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":2,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":3,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":4,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":5,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":7,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":8,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":9,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":10,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":11,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":12,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":13,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.9 billion"},{"run_index":15,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":16,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":17,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":18,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":19,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":20,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":21,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":22,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":23,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":24,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":25,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":26,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":27,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":28,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"},{"run_index":29,"verdict":4,"source":"human","note":"magnitude","answer":"$74.9"}]},{"eval_id":"019e007e-aac9-7785-8c44-edb9f9dfe20d","probe":"What are the total expenses across all governmental activities?","golden":"$154,896","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"$154,696"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"154,896"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$154.896 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"154,896"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$154.696"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$154.896"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$154,896 million"}]},{"eval_id":"019e00a4-d8d8-7d76-84d9-c255fd95f7cd","probe":"How many minutes is Mrs. Trahan recognized for?","golden":"5 minutes","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":4,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":8,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":10,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":12,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 minutes"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":23,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":24,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"3"},{"run_index":29,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"}]},{"eval_id":"019e00a5-ff31-72d6-b137-910bed3336e6","probe":"How many representatives were 'not voting' in Roll No. 20?","golden":"15","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"18"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"18"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":13,"verdict":4,"source":"human","note":"wrong count","answer":"13"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":26,"verdict":4,"source":"human","note":"wrong count","answer":"13"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"}]},{"eval_id":"019e00ac-04dd-7f1d-bcec-9be7f5c1f3ce","probe":"Did Aderholt vote yea or nay?","golden":"yea","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":1,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":2,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":3,"verdict":4,"source":"human","note":"wrong category","answer":"Nay"},{"run_index":4,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":5,"verdict":4,"source":"human","note":"wrong category","answer":"Nay"},{"run_index":6,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":7,"verdict":4,"source":"human","note":"wrong category","answer":"Nay"},{"run_index":8,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":9,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":10,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":11,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":12,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":14,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":16,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":18,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":19,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":20,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":21,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":22,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":23,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":24,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":25,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":26,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"yea"},{"run_index":28,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":29,"verdict":4,"source":"human","note":"wrong category","answer":"nay"}]},{"eval_id":"019e00ac-a893-7e85-9fc2-0de0e7d020dd","probe":"Did Cherfilus-McCormick vote yea or nay?","golden":"nay","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":1,"verdict":4,"source":"human","note":"wrong category","answer":"yea"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":3,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":4,"verdict":4,"source":"human","note":"wrong category","answer":"yea"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":8,"verdict":4,"source":"human","note":"wrong category","answer":"yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":14,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":15,"verdict":4,"source":"human","note":"wrong category","answer":"yea"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":18,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":19,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":20,"verdict":4,"source":"human","note":"wrong category","answer":"yea"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"}]},{"eval_id":"019e00ac-faaf-7e38-b571-92ff92b76932","probe":"Garcia of California voted in which column?","golden":"NAYS","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":4,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Nay"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Nay"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":5,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":6,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":7,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nays"},{"run_index":9,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Nay"},{"run_index":10,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":11,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":12,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":13,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":14,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":15,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":16,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":17,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":18,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":19,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Nay"},{"run_index":20,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":21,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":22,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":23,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":24,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":25,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":26,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":27,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"},{"run_index":28,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":29,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"nay"}]},{"eval_id":"019e00b9-b13c-7e4a-bf11-475eea29d6d3","probe":"Did Senator McConnell vote yea or nay on the final passage of S. 5?","golden":"yea","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":1,"verdict":4,"source":"human","note":"wrong category","answer":"Nay"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":3,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":4,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":5,"verdict":4,"source":"human","note":"wrong category","answer":"Nay"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":7,"verdict":4,"source":"human","note":"wrong category","answer":"Nay"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":10,"verdict":4,"source":"human","note":"wrong category","answer":"Nay"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":13,"verdict":4,"source":"human","note":"wrong category","answer":"Nay"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":16,"verdict":4,"source":"human","note":"wrong category","answer":"Nay"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":21,"verdict":4,"source":"human","note":"wrong category","answer":"nay"},{"run_index":22,"verdict":4,"source":"human","note":"wrong category","answer":"Nay"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":27,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"}]},{"eval_id":"019e00bb-59ee-702a-8cec-38e372b26db8","probe":"How many senators voted YEA on Amendment No. 8?","golden":"75","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":1,"verdict":4,"source":"human","note":"wrong count","answer":"94"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":5,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"75"},{"run_index":7,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":8,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":9,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":10,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":11,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":12,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":13,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":14,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":15,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":16,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":17,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":18,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":19,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":20,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":21,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":22,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":23,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":24,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":25,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":26,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":27,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":28,"verdict":4,"source":"human","note":"wrong count","answer":"64"},{"run_index":29,"verdict":4,"source":"human","note":"wrong count","answer":"64"}]},{"eval_id":"019e00bb-a83a-79e5-808d-25352081e864","probe":"How many senators voted NAY on the final passage of S. 5?","golden":"35","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":8,"verdict":4,"source":"human","note":"wrong count","answer":"25"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":14,"verdict":4,"source":"human","note":"wrong count","answer":"25"},{"run_index":15,"verdict":4,"source":"human","note":"wrong count","answer":"25"},{"run_index":16,"verdict":4,"source":"human","note":"wrong count","answer":"25"},{"run_index":17,"verdict":4,"source":"human","note":"wrong count","answer":"25"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":27,"verdict":4,"source":"human","note":"wrong count","answer":"25"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35"}]},{"eval_id":"019e00c8-3f2a-7e4f-b0e4-86c796356894","probe":"How much did the Connecticut Republican State Central Committee transfer on 9/27/2024?","golden":"$10,000.00","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024.310,000.00"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$10,000.00"},{"run_index":2,"verdict":4,"source":"human","note":"wrong value","answer":"$310,000.00"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"$277,000.00"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024.40"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024.68"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024, $10,000.00"},{"run_index":7,"verdict":4,"source":"human","note":"wrong value","answer":"$127,000.00"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024, $10,000.00"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024, $10,000.00"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024.310,000.00"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"$6,600.00"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024.10"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"$27,000.00"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"$310,000.00"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"$277,000.00"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"$277,000.00"},{"run_index":18,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"$15,000.00"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024, $10,000.00"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"$310,000.00"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"$377,000.00"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"$927,000.00"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"$277,000.00"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024."},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024, $10,000.00"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"$927,2024.310.00.00"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"$927,2024, $10,000.00"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"$27,2024, $10,000.00"}]},{"eval_id":"019e051d-a887-715d-88bf-933cc563b087","probe":"How many nays were there in the vote?","golden":"28","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"30"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":6,"verdict":4,"source":"human","note":"wrong count","answer":"30"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":12,"verdict":4,"source":"human","note":"wrong count","answer":"30"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":20,"verdict":4,"source":"human","note":"wrong count","answer":"30"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"28"},{"run_index":29,"verdict":4,"source":"human","note":"wrong count","answer":"30"}]},{"eval_id":"019e051e-38d3-7d68-9805-50585c912e12","probe":"How would Senator Cruz of Texas have voted if present?","golden":"yea","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong category","answer":"would have voted no."},{"run_index":1,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Yes"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Yes"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Yes"},{"run_index":5,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Yes"},{"run_index":6,"verdict":4,"source":"human","note":"wrong category","answer":"would have voted no"},{"run_index":7,"verdict":4,"source":"human","note":"wrong category","answer":"He would have voted no."},{"run_index":8,"verdict":4,"source":"human","note":"wrong category","answer":"He would have voted no."},{"run_index":9,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Yes"},{"run_index":10,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Yes"},{"run_index":11,"verdict":4,"source":"human","note":"wrong category","answer":"No"},{"run_index":12,"verdict":4,"source":"human","note":"wrong category","answer":"No"},{"run_index":13,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"In the affirmative"},{"run_index":14,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Yes"},{"run_index":15,"verdict":4,"source":"human","note":"wrong category","answer":"Nay"},{"run_index":16,"verdict":4,"source":"human","note":"wrong category","answer":"would have voted no"},{"run_index":17,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Yes"},{"run_index":18,"verdict":4,"source":"human","note":"wrong category","answer":"He would have voted no."},{"run_index":19,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Yes"},{"run_index":20,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Yes"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Yea"},{"run_index":22,"verdict":4,"source":"human","note":"wrong category","answer":"Would have voted no"},{"run_index":23,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"yes"},{"run_index":24,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Yes"},{"run_index":25,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"would have voted yes"},{"run_index":26,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Yes"},{"run_index":27,"verdict":4,"source":"human","note":"wrong category","answer":"He would have voted no."},{"run_index":28,"verdict":4,"source":"human","note":"wrong category","answer":"would have voted no"},{"run_index":29,"verdict":4,"source":"human","note":"wrong category","answer":"would have voted no."}]},{"eval_id":"019e0524-2f26-7e2d-b1d6-9d9e4787d2c7","probe":"How many additional sponsors were added to H.R. 21?","golden":"8","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"26"},{"run_index":1,"verdict":4,"source":"human","note":"wrong count","answer":"3"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"17"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"27"},{"run_index":5,"verdict":4,"source":"human","note":"wrong count","answer":"38"},{"run_index":6,"verdict":4,"source":"human","note":"wrong count","answer":"11"},{"run_index":7,"verdict":4,"source":"human","note":"wrong count","answer":"24"},{"run_index":8,"verdict":4,"source":"human","note":"wrong count","answer":"39"},{"run_index":9,"verdict":4,"source":"human","note":"wrong count","answer":"15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":11,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":13,"verdict":4,"source":"human","note":"wrong count","answer":"24"},{"run_index":14,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":15,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":16,"verdict":4,"source":"human","note":"wrong count","answer":"9"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":18,"verdict":4,"source":"human","note":"wrong count","answer":"3"},{"run_index":19,"verdict":4,"source":"human","note":"wrong count","answer":"28"},{"run_index":20,"verdict":4,"source":"human","note":"wrong count","answer":"9"},{"run_index":21,"verdict":4,"source":"human","note":"wrong count","answer":"6"},{"run_index":22,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":23,"verdict":4,"source":"human","note":"wrong count","answer":"3"},{"run_index":24,"verdict":4,"source":"human","note":"wrong count","answer":"10"},{"run_index":25,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":26,"verdict":4,"source":"human","note":"wrong count","answer":"5"},{"run_index":27,"verdict":4,"source":"human","note":"wrong count","answer":"2"},{"run_index":28,"verdict":4,"source":"human","note":"wrong count","answer":"20"},{"run_index":29,"verdict":4,"source":"human","note":"wrong count","answer":"59"}]},{"eval_id":"019e0529-025b-7daa-a5e9-a453809b33ba","probe":"How many sponsors were added to H. Res. 23?","golden":"15","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":1,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"21"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":4,"verdict":4,"source":"human","note":"wrong count","answer":"21"},{"run_index":5,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":6,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":7,"verdict":4,"source":"human","note":"wrong count","answer":"32"},{"run_index":8,"verdict":4,"source":"human","note":"wrong count","answer":"21"},{"run_index":9,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":10,"verdict":4,"source":"human","note":"wrong count","answer":"5"},{"run_index":11,"verdict":4,"source":"human","note":"wrong count","answer":"5"},{"run_index":12,"verdict":4,"source":"human","note":"wrong count","answer":"1"},{"run_index":13,"verdict":4,"source":"human","note":"wrong count","answer":"21"},{"run_index":14,"verdict":4,"source":"human","note":"wrong count","answer":"3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"15"},{"run_index":16,"verdict":4,"source":"human","note":"wrong count","answer":"16"},{"run_index":17,"verdict":4,"source":"human","note":"wrong count","answer":"18"},{"run_index":18,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":19,"verdict":4,"source":"human","note":"wrong count","answer":"6"},{"run_index":20,"verdict":4,"source":"human","note":"wrong count","answer":"6"},{"run_index":21,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":22,"verdict":4,"source":"human","note":"wrong count","answer":"21"},{"run_index":23,"verdict":4,"source":"human","note":"wrong count","answer":"9"},{"run_index":24,"verdict":4,"source":"human","note":"wrong count","answer":"8"},{"run_index":25,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":26,"verdict":4,"source":"human","note":"wrong count","answer":"14"},{"run_index":27,"verdict":4,"source":"human","note":"wrong count","answer":"12"},{"run_index":28,"verdict":4,"source":"human","note":"wrong count","answer":"21"},{"run_index":29,"verdict":4,"source":"human","note":"wrong count","answer":"8"}]},{"eval_id":"019e055a-a680-7323-8d08-3ac187ccf89f","probe":"What is the rating for IVIG monotherapy when glucocorticoids are contraindicated?","golden":"BIIb","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":14,"verdict":4,"source":"human","note":"wrong spelling","answer":"BIIIb"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":23,"verdict":4,"source":"human","note":"wrong spelling","answer":"BIIIb"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"BIIb"}]},{"eval_id":"019e055f-16e9-7882-9aa1-55c4030f9893","probe":"According to footnote c, in which patients should infliximab NOT be used?","golden":"patients with macrophage activation syndrome","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"In patients with macrophage activation syndrome."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":4,"verdict":4,"source":"human","note":"wrong spelling","answer":"patients with macophage activation syndrome"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":12,"verdict":4,"source":"human","note":"wrong spelling","answer":"patients with macropahage activation syndrome"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":15,"verdict":4,"source":"human","note":"wrong spelling","answer":"patients with macophage activation syndrome"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"In patients with macrophage activation syndrome"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patients with macrophage activation syndrome"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"patients with macrophage activation syndrome"}]},{"eval_id":"019e05ad-fd6c-7734-88ed-1ec50c394ff9","probe":"How many conditions are listed under \"Strong or Consistent Association With Progression to Severe COVID-19\"?","golden":"8","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":5,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":6,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":8,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":9,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":11,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":16,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":17,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":19,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":21,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":23,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":25,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":26,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"},{"run_index":28,"verdict":4,"source":"human","note":"wrong count","answer":"7"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8"}]},{"eval_id":"019e0a8c-68fb-7f92-a952-b3faa7d123a4","probe":"What is the chapter title shown in the header at the top of the page?","golden":"Cell Membrane","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"CELL MEM"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":20,"verdict":4,"source":"human","note":"unwarranted abstention","answer":"not found"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CELL MEMBRANE"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell Membrane"}]},{"eval_id":"019e0ac7-674b-7f8f-ac85-ce02731c302a","probe":"How many stages are shown in the diagram at the top of the page?","golden":"6","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":2,"verdict":4,"source":"human","note":"wrong count","answer":"5"},{"run_index":3,"verdict":4,"source":"human","note":"wrong count","answer":"5 stages"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":6,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Six"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":11,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Six"},{"run_index":12,"verdict":4,"source":"human","note":"wrong count","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":14,"verdict":4,"source":"human","note":"wrong count","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":19,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Six"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":24,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Six"},{"run_index":25,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Six"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6"}]},{"eval_id":"019e0b18-8c5a-7124-bb30-6bd93445411f","probe":"What does the label point to in the middle diagram?","golden":"Cell division accelerates","png_sha":"c97dbfb9dac36762398856cdab61d5779eae44284b94b744c8e56704bbf954e8","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"increased cellular growth"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":24,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"accelerating cell division"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"},{"run_index":28,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"accelerating cell division"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cell division accelerates"}]},{"eval_id":"019e0eaf-c1cd-797e-834b-863d872f236e","probe":"What cell type is shown in the bottom-left image of the diagram?","golden":"Lung cell","png_sha":"7b24760285552c0a3e2beb4a713373cf7079657b1996b630c4cab49bb81d2a0c","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":27,"verdict":4,"source":"human","note":"wrong label","answer":"Thyroid cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lung cell"}]},{"eval_id":"019e0eb7-fc68-7c2e-ad2c-3675d09c8aa1","probe":"What color represents the appendicular skeleton in the diagram's key?","golden":"Purple","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":1,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":3,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"yellow"},{"run_index":5,"verdict":4,"source":"human","note":"wrong value","answer":"yellow"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"purple"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":10,"verdict":4,"source":"human","note":"wrong value","answer":"yellow"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":12,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":13,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":16,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":19,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":20,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":22,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":23,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":24,"verdict":4,"source":"human","note":"wrong value","answer":"green"},{"run_index":25,"verdict":4,"source":"human","note":"wrong value","answer":"yellow"},{"run_index":26,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Purple"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Green"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"Yellow"}]},{"eval_id":"019e0eba-022c-7bba-8967-31ab884feb4d","probe":"What is the bone labeled directly below the Femur in the diagram?","golden":"Patella","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":1,"verdict":4,"source":"human","note":"wrong label","answer":"Tibia"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":3,"verdict":4,"source":"human","note":"wrong label","answer":"Tibia"},{"run_index":4,"verdict":4,"source":"human","note":"wrong label","answer":"Tibia"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":9,"verdict":4,"source":"human","note":"wrong label","answer":"Tibia"},{"run_index":10,"verdict":4,"source":"human","note":"wrong label","answer":"Tibia"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":15,"verdict":4,"source":"human","note":"wrong label","answer":"Tibia"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":26,"verdict":4,"source":"human","note":"wrong label","answer":"Tibia"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Patella"}]},{"eval_id":"019e0eba-8701-7de9-8ba9-578294d6b194","probe":"What is the bone labeled directly between the Clavicle and the Thoracic cage?","golden":"Scapula","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":1,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":2,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":3,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":4,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":5,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":6,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":7,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":8,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":9,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":10,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":11,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":12,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":13,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":14,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":15,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":16,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":17,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":18,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":20,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":21,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Scapula"},{"run_index":23,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":24,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":25,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":26,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":27,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":28,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"},{"run_index":29,"verdict":4,"source":"human","note":"wrong label","answer":"Sternum"}]},{"eval_id":"019e0ec1-bc36-7c2e-a816-0d61d873fe40","probe":"What file name is shown in the WebScope micrograph?","golden":"054 - Peripheral nerve_001.svs","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054-Peripheral nerve_001.svs"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054-Peripheral nerve_001.svs"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":6,"verdict":4,"source":"human","note":"wrong value","answer":"054-Peripheral nerve_001.svg"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":8,"verdict":4,"source":"human","note":"wrong value","answer":"054-Peripheral nerve_001.svg"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":11,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve_001.svg"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":14,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve_001.svg"},{"run_index":15,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve_001.svg"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054-Peripheral nerve_001.svs"},{"run_index":21,"verdict":4,"source":"human","note":"wrong value","answer":"054-Peripheral_nerve_001.svg"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054-Peripheral nerve_001.svs"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":27,"verdict":4,"source":"human","note":"wrong value","answer":"054-Peripheral_001.svg"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"054 - Peripheral nerve_001.svs"},{"run_index":29,"verdict":4,"source":"human","note":"wrong value","answer":"054 - Peripheral nerve_001.svg"}]},{"eval_id":"019e0ec7-9679-765e-943c-61c133fe490f","probe":"Which structure label appears in the rightmost (third) stage of figure (a)?","golden":"Node of Ranvier","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":10,"verdict":4,"source":"human","note":"wrong label","answer":"Myelin"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Node of Ranvier"}]},{"eval_id":"019e0ecc-c17a-7df3-a1f4-407930ed7366","probe":"How many distinct structures are labeled with leader lines on this figure?","golden":"5","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":4,"source":"human","note":"wrong count","answer":"6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e0ee2-00eb-788b-982a-17e9bbe92888","probe":"How many separate cross-section illustrations are shown in Figure 14.1.1","golden":"3","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Three"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":11,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"three"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":14,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"three"},{"run_index":15,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"three"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":22,"verdict":4,"source":"human","note":"wrong count","answer":"4"},{"run_index":23,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Three"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":26,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"three"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3"}]},{"eval_id":"019e0ee9-9d8a-74f4-a4d4-fdae97459d0d","probe":"In panel (c), what three substances flow INTO the cellular respiration mitochondria?","golden":"Blood glucose, Pyruvic acid, Fatty acids","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":4,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":1,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":2,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, pyruvic acid, and fatty acids"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":4,"verdict":4,"source":"human","note":"wrong value","answer":"Oxygen, blood glucose, and fatty acids"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"O2, Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":7,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, pyruvic acid, and fatty acids"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":9,"verdict":4,"source":"human","note":"wrong value","answer":"Oxygen, blood glucose, and pyruvic acid"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":13,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Glucose, Pyruvic Acid, Fatty Acids"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":17,"verdict":4,"source":"human","note":"wrong value","answer":"Oxygen, Pyruvic acid, and Fatty acids."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":20,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid, and Fatty acids"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, pyruvic acid, fatty acids"},{"run_index":23,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic acid and Fatty acids."},{"run_index":24,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, pyruvic acid, and fatty acids"},{"run_index":25,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, pyruvic acid, and fatty acids"},{"run_index":26,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, Pyruvic Acid, and Fatty Acid."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood glucose, Pyruvic acid, Fatty acids"},{"run_index":28,"verdict":4,"source":"human","note":"wrong value","answer":"Oxygen, Pyruvic acid and/or Fatty acids,"},{"run_index":29,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Blood glucose, pyruvic acid, and fatty acids"}]},{"eval_id":"019e0ef1-0b05-7277-bad0-8b16372f30ef","probe":"In Figure 17.5.2, what is the title of item 3b?","golden":"Effects of PTH on kidneys","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":4,"best":2,"cells":[{"run_index":0,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":3,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":4,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":5,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":7,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":8,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":9,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on Kidneys"},{"run_index":11,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":12,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone"},{"run_index":13,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":14,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":15,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":16,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":17,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":18,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":20,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":21,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone"},{"run_index":22,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone"},{"run_index":23,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone."},{"run_index":24,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys:"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effects of PTH on kidneys"},{"run_index":27,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":28,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"},{"run_index":29,"verdict":4,"source":"human","note":"wrong label","answer":"Effects of calcitonin on bone:"}]},{"eval_id":"019de200-d4ba-7ebb-acf4-de78451b07c1","probe":"How many miles is mentioned for relocation of the Executive's principal place of employment?","golden":"25 miles","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":1,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":5,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":6,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":7,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":8,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":9,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":10,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":11,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":12,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":13,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":14,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25)"},{"run_index":15,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":16,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty-five (25) miles"},{"run_index":17,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25)"},{"run_index":18,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":19,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":20,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":21,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25)"},{"run_index":22,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":23,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":24,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":25,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":26,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"},{"run_index":27,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty-five (25) miles"},{"run_index":28,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"\"twenty five (25) miles\""},{"run_index":29,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twenty five (25) miles"}]},{"eval_id":"019de200-d4ce-73b9-b787-b0f7568e7018","probe":"What is the Lessee's telephone number listed in the notices section?","golden":"(81) 8158.8800","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":7,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":8,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":12,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":13,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":14,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":15,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":16,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":20,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":22,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":23,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":24,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":25,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":27,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":28,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8158 8800"}]},{"eval_id":"019de200-d4ec-7fff-aceb-46c812561273","probe":"Which floors of the Building are designated as the Must Take Expansion Premises?","golden":"Floors 5, 6 and 7","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6, and 7"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6, and 7"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":5,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6, and 7"},{"run_index":7,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":8,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6, and 7"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":10,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":12,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6, and 7"},{"run_index":13,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6, and 7"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":18,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6, and 7"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":20,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6, and 7"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":23,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5,6 and 7"},{"run_index":24,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6, and 7"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5,6 and 7"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":27,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"},{"run_index":29,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5, 6 and 7"}]},{"eval_id":"019de200-d511-7272-9565-2412f58e253c","probe":"How often must service area floors be dust mopped, at minimum?","golden":"Once per week","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Weekly"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Weekly"},{"run_index":5,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":6,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":7,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":8,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":9,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":10,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":11,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":12,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":13,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":14,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":15,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":16,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":17,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":18,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":19,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":20,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":21,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":22,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":23,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":24,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":25,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":26,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":27,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Weekly"},{"run_index":28,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"},{"run_index":29,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"weekly"}]},{"eval_id":"019de200-d516-7459-9245-cc659422a55c","probe":"By what time on the Termination Date must the entire outstanding principal of each Revolving Loan be paid?","golden":"12:00 Noon (Eastern time)","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":5,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":6,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":7,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":8,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":10,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":12,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":13,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":14,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":18,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":19,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":20,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":22,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":23,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":24,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":26,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":28,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"12:00 Noon"}]},{"eval_id":"019de200-d51d-7bbb-9bed-8ceaca14c398","probe":"What is the telephone number listed for Mr. Juan Carlos Gonzalez Quezada?","golden":"(81) 8358.7978","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":7,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":8,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":12,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":13,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":14,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":15,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":16,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358-7978"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":20,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":22,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":23,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":24,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":25,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":27,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":28,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8358 7978"}]},{"eval_id":"019de200-d51f-723d-9741-37784d76009a","probe":"What is the telephone number listed for Mr. David Rodriguez Santos at Torre Sienna?","golden":"(81) 8356.1200","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200"},{"run_index":7,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200"},{"run_index":8,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200"},{"run_index":12,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":13,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":14,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":15,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":16,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":20,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200"},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":22,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":23,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200."},{"run_index":24,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356-1200"},{"run_index":25,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":27,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":28,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"(81) 8356 1200"}]},{"eval_id":"019e003d-d1bc-7fb0-a78b-4b79600f8252","probe":"Who is the Custodian of Funds?","golden":"Brad Lander, Comptroller of the City of New York","png_sha":"89c77daf9c6f881f0116f445cbf736cffc12698b60a93b437699a1a075b00138","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":1,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":2,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":3,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":4,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":5,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":6,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":7,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":8,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":9,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":10,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":11,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":12,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":13,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":14,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":15,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":16,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":17,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":18,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":19,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":20,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":21,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":22,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":23,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":24,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":25,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":26,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":27,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":28,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"},{"run_index":29,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brad Lander"}]},{"eval_id":"019e054b-b654-74aa-b2b0-ad19e229a916","probe":"What is the preferred alternative immunomodulator listed for hospitalized patients requiring HFNC oxygen or NIV?","golden":"IV tocilizumab (Blla)","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":7,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":8,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":12,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":13,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":14,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":15,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":19,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":20,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":22,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":23,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":24,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":25,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":26,"verdict":3,"source":"human","note":"answer compressed","answer":"IV tocilizumab"},{"run_index":27,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIlla)"},{"run_index":28,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"IV tocilizumab (BIIa)"}]},{"eval_id":"019e0a6f-0c3e-7520-884b-307d309c1b4b","probe":"What percentage of the human body is oxygen?","golden":"65.0%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":5,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":7,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":8,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":10,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":12,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":13,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":18,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":20,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":23,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":24,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":27,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"},{"run_index":29,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"65.0"}]},{"eval_id":"019e0a70-2afd-7288-98b1-ce3d3fbfaa95","probe":"What percentage of the human body is calcium?","golden":"1.5%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":5,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":7,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":8,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":10,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":12,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":13,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":18,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":20,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":23,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":24,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":27,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"},{"run_index":29,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.5"}]},{"eval_id":"019e0a76-b33e-7648-8be4-ced32e601bf5","probe":"What element is shown in the planetary model?","golden":"Helium (He)","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":5,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":6,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":7,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":8,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":10,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":12,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":13,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":14,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":18,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":19,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":20,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":22,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":23,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":24,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":26,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":28,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"Helium"}]},{"eval_id":"019e0a77-09dc-7990-a971-9e556b040d8c","probe":"What symbol is used to label the electron in the planetary model?","golden":"e\u2212","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":7,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":8,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":12,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":13,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":14,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":15,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":16,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":20,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":22,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":23,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":24,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":25,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":27,"verdict":3,"source":"human","note":"glyph variant","answer":"e\u207b"},{"run_index":28,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"e-"}]},{"eval_id":"019e0a82-da2f-727f-896b-27e752c2b42b","probe":"What are the two types of fatty acids labeled in the phospholipid diagram?","golden":"Saturated fatty acid and unsaturated fatty acid","png_sha":"a2c418cbcdc6704d925ad4ffdd78dee38a58fc1ea68774d0094b65c486a66bf8","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":5,"verdict":3,"source":"human","note":"answer compressed","answer":"Unsaturated and Saturated"},{"run_index":6,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":7,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated fatty acids"},{"run_index":8,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated fatty acids"},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"Unsaturated and Saturated fatty acids"},{"run_index":10,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":12,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Saturated fatty acids and Unsaturated fatty acids"},{"run_index":13,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated fatty acids"},{"run_index":14,"verdict":3,"source":"human","note":"answer compressed","answer":"Unsaturated and Saturated fatty acids"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated fatty acids"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":18,"verdict":3,"source":"human","note":"answer compressed","answer":"Unsaturated and Saturated fatty acids"},{"run_index":19,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":20,"verdict":3,"source":"human","note":"answer compressed","answer":"saturated and unsaturated fatty acid"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":22,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":23,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":24,"verdict":3,"source":"human","note":"answer compressed","answer":"Unsaturated and saturated fatty acids"},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":26,"verdict":3,"source":"human","note":"answer compressed","answer":"Unsaturated and Saturated"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated fatty acids"},{"run_index":28,"verdict":3,"source":"human","note":"answer compressed","answer":"Saturated and Unsaturated"},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"saturated and unsaturated"}]},{"eval_id":"019e0ede-f3cd-7412-8c25-2e079510e6e7","probe":"What is the unit shown on the y-axis label?","golden":"mV (millivolts)","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":5,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":6,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":7,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":8,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":9,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":10,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":11,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":12,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":13,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":14,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":16,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":17,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":18,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":19,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":20,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":22,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":23,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"millivolts (mV)"},{"run_index":24,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":26,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":28,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"mV"}]},{"eval_id":"019e0eea-ac39-7b97-941e-8c1e0a744ae3","probe":"In panel (c), what additional input enters the mitochondria from above (with a downward arrow)?","golden":"O\u2082 (oxygen)","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":3,"best":3,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":5,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":6,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":7,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":8,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Oxygen (O\u2082)"},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":10,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":12,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Oxygen (O2)"},{"run_index":13,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":14,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":18,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Oxygen (O2)"},{"run_index":19,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Oxygen (O\u2082)"},{"run_index":20,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":22,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":23,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Oxygen (O2)"},{"run_index":24,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082"},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082"},{"run_index":26,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":28,"verdict":3,"source":"human","note":"answer compressed","answer":"O2"},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"O\u2082"}]},{"eval_id":"019de200-d495-7bf0-9c87-96d57c098e71","probe":"What section is referenced for the definition of 'Threshold Successors'?","golden":"Section 10.1","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10.1"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":13,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10.1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10.1"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10.1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10.1"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10.1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10.1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 10.1"}]},{"eval_id":"019de200-d496-74b2-a2cc-5c7a6982836d","probe":"What is the Tenant Notice Address suite number?","golden":"Suite 900","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":8,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"900"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 900"}]},{"eval_id":"019de200-d4ac-742d-b65a-74bd92f2893d","probe":"What is the name of the broker listed in Section 31?","golden":"Cresa Global, Inc.","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"Cresa Global, Inc"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cresa Global, Inc."},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"Cresa Global, Inc"}]},{"eval_id":"019de200-d4c1-76bf-b140-f4b73e70f7ed","probe":"What is the maximum sound level (in dBA) allowed for vacuum cleaners?","golden":"70dBA","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"70"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":23,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"70"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70dBA"}]},{"eval_id":"019de200-d4c5-7b98-9a5a-c76d5fb5ae1e","probe":"What is the title of section 5.2?","golden":"Operating Expenses; Consumable Expenses and Base Building Expenses","png_sha":"3343506981bd41f08b63b8df40f8ba763e2bc1566a850d0903f24b1c5782cf77","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":7,"verdict":3,"source":"human","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":20,"verdict":3,"source":"human","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Operating Expenses; Consumable Expenses and Base Building Expenses."},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"Operating Expenses: Consumable Expenses and Base Building Expenses"}]},{"eval_id":"019de200-d4cb-70dc-a225-ac7807b5a70c","probe":"What is the title of Article 33?","golden":"Costs and Attorneys' Fees","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"Costs and Attorneys\u2019 Fees"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Costs and Attorneys' Fees"}]},{"eval_id":"019de200-d4d6-77e1-9296-5f9e11cf7728","probe":"What does item (c) say?","golden":"Intentionally deleted.","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Intentionally deleted.\""},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":18,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Intentionally deleted"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Intentionally deleted.\""},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Intentionally deleted.\""},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Intentionally deleted.\""},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intentionally deleted."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."},{"run_index":28,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Intentionally deleted"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(c) Intentionally deleted."}]},{"eval_id":"019de200-d4d7-71ee-b89a-13f57933c5ed","probe":"What is the company name shown in the headers of the financial statements?","golden":"Acadia Realty Trust and Subsidiaries","png_sha":"d99abf4bae64753a77c680d1e83acdbdc08eb377e9da9bc0a4af8337f67971e2","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"Acadia Realty Trust"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":6,"verdict":3,"source":"human","note":"answer compressed","answer":"Acadia Realty Trust"},{"run_index":7,"verdict":3,"source":"human","note":"answer compressed","answer":"Acadia Realty Trust"},{"run_index":8,"verdict":3,"source":"human","note":"answer compressed","answer":"Acadia Realty Trust"},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"ACADIA REALTY TRUST"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"Acadia Realty Trust"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":13,"verdict":3,"source":"human","note":"answer compressed","answer":"Acadia Realty Trust"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"ACADIA REALTY TRUST"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"Acadia Realty Trust"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"Acadia Realty Trust"},{"run_index":18,"verdict":3,"source":"human","note":"answer compressed","answer":"Acadia Realty Trust"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":20,"verdict":3,"source":"human","note":"answer compressed","answer":"Acadia Realty Trust"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":23,"verdict":3,"source":"human","note":"answer compressed","answer":"Acadia Realty Trust"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST AND SUBSIDIARIES"},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"Acadia Realty Trust"}]},{"eval_id":"019de200-d4e2-7aab-ae79-29c74e645fca","probe":"What is the title of Exhibit C?","golden":"Technology Exhibit","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":5,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"EXHIBIT C: TECHNOLOGY"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TECHNOLOGY EXHIBIT"},{"run_index":28,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"EXHIBIT C: TECHNOLOGY"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Technology Exhibit"}]},{"eval_id":"019de200-d4e7-7aba-997b-697fce37c98b","probe":"Who signed as Chief Executive Officer of 1847 Holdings LLC?","golden":"Ellery W. Roberts","png_sha":"17421f00db7e68e09f420ba5abd403a8bc79b47f8f380327515bff5297f38fed","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"Ellery W Roberts"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":8,"verdict":3,"source":"human","note":"glyph variant","answer":"Ellery W Roberts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ellery W. Roberts"}]},{"eval_id":"019de200-d4f1-7b08-800d-39648227b1fc","probe":"How many days advance notice must Tenant give for an Acceleration Notice?","golden":"120 days","png_sha":"dc940503d0f2337bdbcc0f2524caf3e8d7a5dadd21a251835c7807f47112d74a","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":5,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"One hundred twenty (120) days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"120"},{"run_index":18,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"One Hundred Twenty (120) days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":20,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"one hundred twenty (120) days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"120 days"}]},{"eval_id":"019de200-d502-7a8b-9ba6-c9892e2eeecc","probe":"What insurance form is the general liability insurance to be written on?","golden":"2001 Insurance Services Office form","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":12,"verdict":3,"source":"human","note":"answer compressed","answer":"2001 Insurance Services Office"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"2001 Insurance Services Office"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2001 Insurance Services Office form"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 2001 Insurance Services Office form"}]},{"eval_id":"019de200-d505-7a87-bf67-4ac7fc6b2fd3","probe":"How many days before policy expiration must original copies of policies be delivered to Landlord?","golden":"fifteen (15) days","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"15 days"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":6,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen (15)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":8,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"15 days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":14,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen (15)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":23,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen (15)"},{"run_index":24,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen (15)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"fifteen (15) days"},{"run_index":29,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"fifteen (15)"}]},{"eval_id":"019de200-d507-733d-8d8c-87040ba6130c","probe":"How many days does Landlord have to give Tenant a termination notice after submission of the statement?","golden":"30 days","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":1,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":3,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Thirty (30) days"},{"run_index":4,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":5,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":6,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":7,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":8,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":9,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":10,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":11,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":12,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":13,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":14,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":15,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":16,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":17,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":18,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":19,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":20,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":21,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":22,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":23,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":24,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":25,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":26,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":27,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30) days"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 days"},{"run_index":29,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"thirty (30)"}]},{"eval_id":"019de200-d508-7af1-93e1-8436c404657e","probe":"How many business days in advance must Tenant provide the Notice of Permitted Transfer?","golden":"10 Business Days","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 business days"},{"run_index":20,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10"},{"run_index":21,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Ten"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"10"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 Business Days"}]},{"eval_id":"019de200-d50e-7050-b563-d96d07356800","probe":"How many times per day must the exterior of the building be inspected and maintained?","golden":"four times per day","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Four times."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Four times"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Four."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four times"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Four times"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":13,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four times"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Four times"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four times"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"four times"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four times per day"}]},{"eval_id":"019de200-d514-76a5-be6d-0713d4261c08","probe":"What is the full deadline (both time of day and number of business days) by which a Notice of Borrowing must be delivered before a proposed borrowing?","golden":"1:00 p.m. (Eastern time) two (2) Business Days prior","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of the proposed borrowing."},{"run_index":5,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":6,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":7,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":8,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 PM (Eastern Time) two Business Days prior"},{"run_index":10,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":12,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":14,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":18,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":19,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern Time) two (2) Business Days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 PM two Business Days"},{"run_index":22,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":23,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m. (Eastern time) two (2) Business Days prior"},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern Time) two (2) Business Days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Before 1:00 p.m. (Eastern time) two (2) Business Days prior to the date of the proposed borrowing."},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"},{"run_index":28,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 PM (Eastern time) two Business Days prior"},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"1:00 p.m. (Eastern time) two (2) Business Days"}]},{"eval_id":"019de200-d515-7626-bd30-2e0c3b0c3b7f","probe":"Within how many Business Days must Borrower pay any excess if it results from a reserve against the Borrowing Base?","golden":"five (5) Business Days","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five (5) Business Days"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":6,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":7,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":8,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"five"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"five (5) Business Days"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"Five business days"},{"run_index":12,"verdict":3,"source":"human","note":"answer compressed","answer":"Five Business Days"},{"run_index":13,"verdict":3,"source":"human","note":"answer compressed","answer":"five"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"Five business days"},{"run_index":18,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":19,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":20,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":22,"verdict":3,"source":"human","note":"answer compressed","answer":"Five business days"},{"run_index":23,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":24,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Within five (5) Business Days"},{"run_index":27,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"5"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"five (5)"},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"Five"}]},{"eval_id":"019de200-d518-778a-9421-02c7d2e3a05a","probe":"What is the section number for 'Time is of the Essence'?","golden":"Section 1.4","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":7,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":10,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":18,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":20,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4."},{"run_index":24,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 1.4"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"},{"run_index":29,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.4"}]},{"eval_id":"019de200-d523-7d03-9cf0-aa0eb615e454","probe":"Within how many calendar days following lease termination must Lessor conduct and deliver the Phase I environmental assessment under section 11.4?","golden":"fifteen (15) calendar days","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Fifteen (15)"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"15 calendar days"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":5,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Fifteen (15)"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Within fifteen (15) calendar days"},{"run_index":8,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Fifteen (15)"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Within fifteen (15) calendar days"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":12,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":13,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Fifteen (15)"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Fifteen (15)"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":18,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Fifteen (15)"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Fifteen (15)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Within fifteen (15) calendar days"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"Fifteen (15)"},{"run_index":23,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Within fifteen (15) calendar days"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"(15) calendar days"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"fifteen (15)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fifteen (15) calendar days"}]},{"eval_id":"019de778-2487-7ceb-942f-bbc9cce683b5","probe":"What is the public law number?","golden":"118-109","png_sha":"a0300e50b30b31b24996ac843a50187dca0d8e81f6c026161ae3e07159e9815a","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"118\u2013109"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":8,"verdict":3,"source":"human","note":"glyph variant","answer":"118\u2013109"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"118\u2013109"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"118\u2013109"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":24,"verdict":3,"source":"human","note":"glyph variant","answer":"118\u2013109"},{"run_index":25,"verdict":3,"source":"human","note":"glyph variant","answer":"118\u2013109"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"118-109"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"118\u2013109"}]},{"eval_id":"019dfaef-4f26-7d15-9caf-4928cafc4f5e","probe":"What is the exhibit number shown at the top right of this page?","golden":"Exhibit 23.1","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":5,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":8,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":10,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":12,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit 23.1"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":18,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":20,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":23,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":24,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":27,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"},{"run_index":29,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"23.1"}]},{"eval_id":"019dfb1d-fe01-7745-a248-c6531ebdce43","probe":"What act is referenced as the source of the 'forward-looking statements' definition?","golden":"Private Securities Litigation Reform Act of 1995","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Private Securities Litigation Reform Act of 1995"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":22,"verdict":3,"source":"human","note":"answer compressed","answer":"Private Securities Litigation Reform Act"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Private Securities Litigation Reform Act of 1995"},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"Private Securities Litigation Reform Act"}]},{"eval_id":"019dfb3d-df1d-70c3-8680-871f110c4e18","probe":"How many state departments are involved in the ACFR production, according to the letter?","golden":"more than 200","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"over 200"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"over 200"},{"run_index":2,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"More than 200"},{"run_index":6,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"over 200"},{"run_index":7,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"over 200"},{"run_index":8,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":9,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":10,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"over 200"},{"run_index":11,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":12,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"over 200"},{"run_index":13,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":14,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":15,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"over 200"},{"run_index":16,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":17,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":18,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":19,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":20,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":21,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"over 200"},{"run_index":22,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":23,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"over 200"},{"run_index":24,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":25,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":26,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"over 200"},{"run_index":27,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Over 200"},{"run_index":28,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"over 200"},{"run_index":29,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"over 200"}]},{"eval_id":"019dfb3f-d06a-7547-a4b6-8a6e4c150c61","probe":"What is the suite number of the office address listed at the bottom of the letter?","golden":"Suite 1850","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":5,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":7,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":8,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":10,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Suite 1850"},{"run_index":13,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":18,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":20,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":23,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":24,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":27,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"},{"run_index":29,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1850"}]},{"eval_id":"019dffff-131f-7d34-8e0c-2be25da41c0d","probe":"What two courts are shown at the bottom level under County-Level Courts?","golden":"Municipal Courts and Justice of the Peace Courts","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":7,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Municipal Courts, Justice of the Peace Courts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Municipal Courts and Justice of the Peace Courts"}]},{"eval_id":"019e0006-0655-7fe4-88c4-d697fbcb759a","probe":"How many Council Members does Queens have?","golden":"14 Members","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":4,"verdict":3,"source":"human","note":"answer expanded","answer":"14 Council Members"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":17,"verdict":3,"source":"human","note":"answer expanded","answer":"14 Council Members"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"14"},{"run_index":22,"verdict":3,"source":"human","note":"answer expanded","answer":"14 Council Members"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"},{"run_index":28,"verdict":3,"source":"human","note":"answer expanded","answer":"14 Council Members"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14 Members"}]},{"eval_id":"019e001b-77bc-7c11-843b-51dfbbec15c3","probe":"Who signed this letter?","golden":"Mayor Brandon Johnson","png_sha":"781c6fcbd4f3164179bf71cd942ca2e9794fc7c49c6bbcf883dd13f2ce626331","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":18,"verdict":3,"source":"human","note":"title/honorific handling","answer":"Brandon Johnson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mayor Brandon Johnson"}]},{"eval_id":"019e002a-8546-75d0-9290-e4f34687786f","probe":"What year ended is referenced at the top of the page?","golden":"December 31, 2024","png_sha":"4ceaa28bf7551920a1890b7fbf19a27b1cc875ad22828548d20d5021ffb4cb9e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":13,"verdict":3,"source":"human","note":"answer compressed","answer":"2024"},{"run_index":14,"verdict":3,"source":"human","note":"answer compressed","answer":"2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2024"}]},{"eval_id":"019e0046-8a1d-76f7-a894-dfdf17c5e779","probe":"What is the As Previously Stated Unrestricted (Deficit) amount (in thousands of dollars)?","golden":"(33,888,893)","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":1,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":5,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":6,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":7,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":8,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":10,"verdict":3,"source":"auto","note":"no normalized substring match","answer":"33,888,893"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":12,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":13,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":14,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":15,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":16,"verdict":3,"source":"human","note":"glyph variant","answer":"-33,888,893"},{"run_index":17,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":19,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":20,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"-33,888,893"},{"run_index":22,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":23,"verdict":3,"source":"auto","note":"no normalized substring match","answer":"33,888,893"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":25,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"-33,888,893"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(33,888,893)"},{"run_index":28,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"},{"run_index":29,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"33,888,893"}]},{"eval_id":"019e0049-7334-7204-a87d-cdd77f11d1df","probe":"What is the As Restated Total Net (Deficit)/Position amount (in thousands)?","golden":"$(30,877,248)","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"30,877,248"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(30,877,248)"}]},{"eval_id":"019e0085-cd0d-7043-93eb-a33714bb645a","probe":"What GASB Statement number did the Council adopt in fiscal year 2024?","golden":"No. 96","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":1,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GASB Statement No. 96"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":5,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":7,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":8,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":10,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Statement No. 96"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Statement No. 96"},{"run_index":13,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Statement No. 96"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Statement No. 96"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":18,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":20,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"No. 96"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Statement No. 96"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":27,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"},{"run_index":29,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"96"}]},{"eval_id":"019e00a2-46eb-7c4d-93dc-be4b015c5931","probe":"Until what time may morning-hour debate continue?","golden":"11:50 a.m.","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"11:50 am"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"11:50 a.m."}]},{"eval_id":"019e055d-286a-7563-a7e4-fcf6471dab8b","probe":"What is the dose of infliximab listed for intensification therapy?","golden":"5\u201310 mg/kg IV for 1 dose","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":7,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":8,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":15,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":20,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":23,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg IV for 1 dose"},{"run_index":25,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":27,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":28,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg IV for 1 dose"}]},{"eval_id":"019e055e-28ea-7f76-943f-b37787cd73cb","probe":"What is the IV dose range for high-dose anakinra?","golden":"5\u201310 mg/kg/day","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg/day"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":14,"verdict":3,"source":"human","note":"answer expanded","answer":"5-10 mg/kg/day IV"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"5-10 mg/kg/day"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":20,"verdict":3,"source":"human","note":"answer expanded","answer":"5-10 mg/kg/day IV"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":23,"verdict":3,"source":"human","note":"answer expanded","answer":"5-10 mg/kg/day IV"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5\u201310 mg/kg/day IV"}]},{"eval_id":"019e05ac-b930-79c4-93f6-be96e504477e","probe":"Within how many months of a recent SARS-CoV-2 infection may substantial immunity be conferred, according to footnote b?","golden":"3-6 months","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"within 3\u20136 months"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Within 3-6 months"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Within 3-6 months"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":14,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3-6 months"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"3\u20136 months"}]},{"eval_id":"019e05b5-b5f0-7a24-b00b-652882db4074","probe":"What plateau pressure does the Panel recommend targeting?","golden":"<30 cm H2O","png_sha":"f2687af1be946044a236b7f11f8cf6f728ef1c4e9e442378d2a6ad846b6a54e4","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":7,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":8,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":13,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":14,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":16,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":20,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":23,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":24,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":25,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":27,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"<30 cm H2O"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"<30 cm H\u2082O"}]},{"eval_id":"019e05e7-ce2c-772c-8efd-a4776364273c","probe":"What is the figure number for the blood pressure image?","golden":"Figure 1.0","png_sha":"4fb66d797829b4efe7d38ed6d367871d6664885f70ef83a42d3f0dfec31552e6","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":5,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":16,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":20,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Figure 1.0"}]},{"eval_id":"019e05e9-158a-7e0b-a377-74df9d26138b","probe":"How many abdominal regions are shown in figure (a)?","golden":"nine","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":6,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":7,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":8,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":9,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":10,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":11,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":14,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":16,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":17,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":21,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":22,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nine"},{"run_index":25,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":26,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"9"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nine"}]},{"eval_id":"019e05f4-56d1-7193-845a-2889286704f6","probe":"How many abdominal quadrants are shown in figure (b)?","golden":"four","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Four"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":19,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":27,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"4"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"four"}]},{"eval_id":"019e05f7-dd30-7195-830e-cd261e20c2b7","probe":"What organ system is shown as the example at the Organ system level?","golden":"Urinary tract system","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":19,"verdict":3,"source":"human","note":"answer compressed","answer":"Urinary system"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Urinary tract system"}]},{"eval_id":"019e0a70-8117-7662-8777-c2511bc6f2ee","probe":"What percentage of the human body is phosphorus?","golden":"1.0%","png_sha":"77546607ad7b6878fa8ca372a4cbabfce2632304d27f3e1d30abdcdab7d7624a","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":2,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":3,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":4,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":6,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":7,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":9,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":10,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":11,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":12,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":13,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":14,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":15,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1.0%"},{"run_index":17,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":18,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":19,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":20,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":21,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":22,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":23,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":24,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":25,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":26,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":27,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":28,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"},{"run_index":29,"verdict":3,"source":"human","note":"unit/prefix in probe","answer":"1.0"}]},{"eval_id":"019e0a77-521b-7c1e-96e5-0fcfd2acccfb","probe":"How many positive charges are shown in the nucleus of the electron cloud model?","golden":"2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":2,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"two"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":9,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Two"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":11,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"two"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":18,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Two"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":20,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"two"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":23,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"two"},{"run_index":24,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"two"},{"run_index":25,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Two"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":29,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Two"}]},{"eval_id":"019e0a9e-aa0f-7a55-89e3-a0cd7f73e21f","probe":"What chemical formula is shown next to each red blood cell in the bottom row of Figure 3.1.6?","golden":"H2O","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":12,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":14,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":15,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":23,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":24,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":27,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H2O"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"H\u2082O"}]},{"eval_id":"019e0ac6-e7e3-7800-ac52-eee064e4e8b7","probe":"What is the scale bar length shown in the microscope images?","golden":"5 \u03bcm","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":1,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":8,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":12,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":13,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":20,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 \u03bcm"},{"run_index":25,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":27,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":28,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"5 \u00b5m"}]},{"eval_id":"019e0ad4-4005-7307-aae9-78e3049f1a65","probe":"What are the three lines that pluripotent embryonic stem cells differentiate into?","golden":"Endoderm, Mesoderm, and Ectoderm","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Endoderm, Mesoderm, and Ectoderm"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Endoderm, Mesoderm, and Ectoderm"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Endoderm, Mesoderm, and Ectoderm"},{"run_index":3,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":4,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":5,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":6,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":7,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":8,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":9,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":10,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":11,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":12,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, and Ectoderm line"},{"run_index":13,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":14,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":15,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":16,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":17,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":18,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":19,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":20,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Endoderm, Mesoderm, and Ectoderm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Endoderm, Mesoderm, and Ectoderm"},{"run_index":23,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Endoderm, Mesoderm, and Ectoderm"},{"run_index":25,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"},{"run_index":26,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":27,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line."},{"run_index":28,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Endoderm, Mesoderm, Ectoderm"},{"run_index":29,"verdict":3,"source":"human","note":"equivalent phrasing","answer":"Endoderm line, Mesoderm line, Ectoderm line"}]},{"eval_id":"019e0ec6-5ccb-7a48-a454-ea039c311db0","probe":"In the leftmost (first) stage of figure (a), what two structures are labeled?","golden":"Nucleus and Axon","png_sha":"53d02863c9fa55e2828442cddcbfdba80d8da7500e2258ddb1c2c3a78dc007b6","worst":3,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":20,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Nucleus, Axon"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and axon."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"},{"run_index":28,"verdict":3,"source":"human","note":"list separator/conjunction","answer":"Nucleus, Axon"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus and Axon"}]},{"eval_id":"019e0ed6-d0db-7047-a35c-28a5f0394d4e","probe":"How many cranial nerves are labeled in this figure?","golden":"12","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Twelve"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":5,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Twelve"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":8,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"twelve"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":13,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Twelve"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":19,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Twelve"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":22,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Twelve"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":27,"verdict":3,"source":"human","note":"numeral/spelled-out","answer":"Twelve"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12"}]},{"eval_id":"019e0eea-1322-709e-b1c1-430100607e7d","probe":"In panel (c), what four products come OUT of cellular respiration?","golden":"ATP, Heat, CO\u2082, H\u2082O","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":2,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":3,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":4,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":5,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":6,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":7,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ATP, Heat, CO\u2082, H\u2082O"},{"run_index":9,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":10,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":11,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, and H2O"},{"run_index":12,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, and H2O"},{"run_index":13,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":14,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":15,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":16,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":17,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":18,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":19,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO_2, H_2O"},{"run_index":20,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":21,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":22,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, and H2O"},{"run_index":23,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, and H2O"},{"run_index":24,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":25,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":26,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":27,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":28,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"},{"run_index":29,"verdict":3,"source":"human","note":"glyph variant","answer":"ATP, Heat, CO2, H2O"}]},{"eval_id":"019e0ef0-10bf-71af-9ca6-cd2d668f1d1c","probe":"In Figure 17.5.2, what does step 6 describe the effects of?","golden":"calcitonin on bone","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":3,"best":2,"cells":[{"run_index":0,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":1,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":2,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":3,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":4,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":5,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":6,"verdict":3,"source":"human","note":"answer compressed","answer":"Calcitonin"},{"run_index":7,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":8,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":9,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":10,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":11,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":12,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":13,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":15,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":16,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":17,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":18,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"calcitonin on bone"},{"run_index":20,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":21,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":22,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":23,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":24,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":25,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":26,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":27,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":28,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"},{"run_index":29,"verdict":3,"source":"human","note":"answer compressed","answer":"calcitonin"}]},{"eval_id":"019de200-d48b-7a0c-9e79-d846c27a96b5","probe":"What page does Article XI Security Deposit start on?","golden":"50","png_sha":"625ba89847b64383ae07efde4a0b7374c88fd2b6dcff552df6812dad32d03160","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"50"}]},{"eval_id":"019de200-d48d-703c-b522-b34424519003","probe":"What is Exhibit L?","golden":"Competitor List","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Competitor List"}]},{"eval_id":"019de200-d48e-767a-b928-9b2d12086653","probe":"What is Exhibit H?","golden":"Roof Access Agreement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Roof Access Agreement"}]},{"eval_id":"019de200-d48f-7596-abf5-cacd23054c4d","probe":"What is Exhibit J?","golden":"Parking Easement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Parking Easement"}]},{"eval_id":"019de200-d490-71ff-a39d-ee962a11796e","probe":"What is Exhibit D?","golden":"Certificate Affirming the Must Take Commencement Date","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exhibit D is the \"Certificate Affirming the Must Take Commencement Date\"."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certificate Affirming the Must Take Commencement Date"}]},{"eval_id":"019de200-d491-71d6-875d-4fa564623978","probe":"What is Exhibit B?","golden":"Work Agreement","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Work Agreement"}]},{"eval_id":"019de200-d492-726b-87fc-5718790d5ebd","probe":"What is Exhibit E?","golden":"Measurement Schedule","png_sha":"a8e130a4342c04df13dc08481900f47dfd4693fad6e62aaa148dd0dc590e5eb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Measurement Schedule"}]},{"eval_id":"019de200-d494-73d8-930e-be33d26373fa","probe":"What section is referenced for the definition of 'Tax Benefits'?","golden":"Section 5.6","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 5.6"}]},{"eval_id":"019de200-d497-758c-9ad2-fceee7efd1fa","probe":"What section is referenced for the definition of 'Tenant's Plans'?","golden":"Section 9.4(a)","png_sha":"a508ae5542402955ad1a5d6456d0dabd524989e0a6ad28c4e9bba5c1212ec716","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Section 9.4(a)"}]},{"eval_id":"019de200-d498-741d-b3e0-3374c9b02dfc","probe":"What is the title of section H?","golden":"Tenant Modular Furniture","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT MODULAR FURNITURE"}]},{"eval_id":"019de200-d499-74c0-a9b3-74b464fcf74b","probe":"What is the color name listed for the carpet base?","golden":"503 Ginger","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"503 Ginger"}]},{"eval_id":"019de200-d49a-7b22-8b95-3fe120b21efc","probe":"What is the section number for the CARPET section?","golden":"09680","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09680"}]},{"eval_id":"019de200-d49c-75ca-963f-0649d0c70719","probe":"What is the section number for ACOUSTICAL CEILING?","golden":"09510","png_sha":"f1d810eb3d207ad749a47e7155b5a1dabf4aff7400a440d399b782ac32308a77","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"09510"}]},{"eval_id":"019de200-d49d-7cee-91a2-4ed07626e90a","probe":"What is the name of the company shown in the schedule heading on this page?","golden":"Acadia Realty Trust","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ACADIA REALTY TRUST"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acadia Realty Trust"}]},{"eval_id":"019de200-d49e-7120-8c57-be2e37f1a894","probe":"What is the page number shown at the bottom of the upper section of this page?","golden":"166","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"166"}]},{"eval_id":"019de200-d49f-72ce-9b9d-97ba16d5640c","probe":"What is the depreciation period (useful life in years) listed in the rightmost column for every property on this page?","golden":"40 years","png_sha":"3cae8562bad2632baba717fbcf6f5933a567063ce35309a730df6094ef0712af","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years for every property"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"40 years"}]},{"eval_id":"019de200-d4a0-7403-856e-aa22d2bdae81","probe":"What is the name of the company shown at the top of the page?","golden":"Acceleron Pharma Inc.","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Acceleron Pharma Inc."}]},{"eval_id":"019de200-d4a1-7f82-aa55-38eac3b9b487","probe":"What is the total deferred tax assets for 2017 (in thousands)?","golden":"145,657","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$145,657"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$145,657"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,657"}]},{"eval_id":"019de200-d4a2-7a39-91ad-766fdf7c2010","probe":"What is the page number shown at the bottom center of the page?","golden":"F-29","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"F-29"}]},{"eval_id":"019de200-d4a3-7518-9715-cc1bb9edb084","probe":"What is the deferred revenue amount for 2016 (in thousands)?","golden":"1,666","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1666"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,666"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,666"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,666"}]},{"eval_id":"019de200-d4a4-7cca-a0e9-a3ce81d8b684","probe":"What is the federal income tax expense at the statutory rate for 2015?","golden":"34.0%","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0 %"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0 %"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0 %"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0 %"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0 %"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"34.0%"}]},{"eval_id":"019de200-d4a5-753e-87a5-2c51cb711be4","probe":"What is the Research and development credits amount for 2017 (in thousands)?","golden":"12,548","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,548"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,548"}]},{"eval_id":"019de200-d4a6-72d4-b715-3cd7f42e4f66","probe":"What is the State income tax, net of federal benefit percentage for 2016?","golden":"5.9%","png_sha":"4fef6772c591e0d1263f042907b6b04fdb33686e93865d1666088b44f9963185","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9 %"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9 %"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.9%"}]},{"eval_id":"019de200-d4a7-74af-afa8-d3ad189499cc","probe":"What is the deposit amount mentioned in this document?","golden":"$500,000.00","png_sha":"5a5e3841491b2b356eb9b963e45419183ebf6ffae298e69a6f9dd5488bc23e1c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Five Hundred Thousand and 00/100 Dollars ($500,000.00)"}]},{"eval_id":"019de200-d4a8-7bdc-bc00-d50a60d60dcc","probe":"What is the title of section 16?","golden":"Mutual Waiver of Subrogation Rights","png_sha":"674a83793665d045c76513a816f7fc9099c52baccd94af7ee817a5f89cdc81d5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mutual Waiver of Subrogation Rights"}]},{"eval_id":"019de200-d4a9-7107-917d-4d1e160c26b3","probe":"What is the anticipated commencement date?","golden":"March 1, 2016","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"March 1, 2016"}]},{"eval_id":"019de200-d4aa-7225-85f5-76e6b1382af9","probe":"What is the premises address?","golden":"2665 North First Street, Suite 300, San Jose, California 95134","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300, San Jose, California 95134"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2665 North First Street, Suite 300 San Jose, California 95134"}]},{"eval_id":"019de200-d4ab-727c-ae0c-07bdc5f94836","probe":"What is the tenant's trade name?","golden":"8x8, Inc.","png_sha":"bf8cd11e4ce3acb933bc1a41479e59f0dc7fd0e556b460b8a8fd2ab2f0b7c466","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8x8, Inc."}]},{"eval_id":"019de200-d4ad-71b2-aae9-616c2d5fdb91","probe":"What is the title of Section 33?","golden":"Holding Over","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Holding Over"}]},{"eval_id":"019de200-d4ae-7bb5-8e56-dfba0d289a6a","probe":"What is the title of Section 38?","golden":"Miscellaneous","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Miscellaneous"}]},{"eval_id":"019de200-d4af-7ae9-9bf2-f9ad2d8f5ea5","probe":"What is the title of Section 32?","golden":"Estoppel Certificate","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Estoppel Certificate"}]},{"eval_id":"019de200-d4b0-7068-9693-c265751b0823","probe":"What is the title of Section 34?","golden":"Assignment and Subletting","png_sha":"9159137a8f917d688c6248db2a2452a9465179b9fa549d4beb2d738378737b0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"}]},{"eval_id":"019de200-d4b2-7946-80ee-a29424252d23","probe":"What is the title of section 14.3?","golden":"Transfer Premium","png_sha":"cde4659cf5512e2c7b127af66eb4bab815dcc533bb04fce540d6d56b21cbb6cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Transfer Premium"}]},{"eval_id":"019de200-d4b3-7330-8b3a-3010528a30fa","probe":"What is the title of section 14.5?","golden":"Effect of Transfer","png_sha":"cde4659cf5512e2c7b127af66eb4bab815dcc533bb04fce540d6d56b21cbb6cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Effect of Transfer"}]},{"eval_id":"019de200-d4b4-702e-932f-bb5b6dbb2b20","probe":"What is the title of Article XXIX?","golden":"Expansion Rights","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EXPANSION RIGHTS"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Expansion Rights"}]},{"eval_id":"019de200-d4b6-73e9-aa56-a2eb7119541a","probe":"What is the title of Section 29.1?","golden":"Right of First Refusal","png_sha":"4da63ef7114b46b2feb4908e76162410ff886e1d54b42e83b895f5f3ede0bbe7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The title of Section 29.1 is \"Right of First Refusal.\""},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Right of First Refusal"}]},{"eval_id":"019de200-d4b8-7164-91b2-3ec03d9f397f","probe":"What is the title of section 12?","golden":"Severance Payments","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severance Payments"}]},{"eval_id":"019de200-d4b9-723f-8a38-4f373e93bffa","probe":"What is the title of section 13?","golden":"Certain Covenants of the Executive","png_sha":"608e4c3eb9309b7b7dc3ae966415ef0ebf692ba3342d8af4263a366ce0bd5f95","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Certain Covenants of the Executive"}]},{"eval_id":"019de200-d4bc-76fc-9589-06797f38e895","probe":"What is the title of section E?","golden":"UNIFORMS","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"E. UNIFORMS"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"E. UNIFORMS"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"E. UNIFORMS"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"E. UNIFORMS"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"E. UNIFORMS"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Uniforms"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"E. UNIFORMS"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"E. UNIFORMS"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"E. UNIFORMS"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"UNIFORMS"}]},{"eval_id":"019de200-d4be-7e4d-b5ce-bf5d0d9e3745","probe":"What is the title of section J?","golden":"LIGHTING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lighting"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIGHTING"}]},{"eval_id":"019de200-d4bf-7a42-91f9-d00fe759f635","probe":"What is the title of section H?","golden":"SECURITY AND INCIDENT REPORTING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Security and Incident Reporting"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SECURITY AND INCIDENT REPORTING"}]},{"eval_id":"019de200-d4c0-7843-8047-cc09e991e12b","probe":"What is the title of section K?","golden":"GREEN CLEANING","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green Cleaning"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green Cleaning"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green Cleaning"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GREEN CLEANING"}]},{"eval_id":"019de200-d4c2-7ad3-88a8-ed0b24b345b7","probe":"What is the item number for the men's Foreperson/Day Porter Pleated dress pants?","golden":"#865","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#865"}]},{"eval_id":"019de200-d4c3-7771-b087-cb7f248214a4","probe":"What is the item number listed for the women's Long Sleeve Dress Blouse?","golden":"#528","png_sha":"3f8a360c3768a13e7e83e98c1f113680152edfe329ecf7453458751208c8af4d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\nEVIDENCE \"Women...Long Sleeve Dress Blouse - #528\""},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528\nEVIDENCE \"Women Foreperson/Day Matron \u2014 Long Sleeve Dress Blouse - #528\""},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"#528"}]},{"eval_id":"019de200-d4c4-736b-b432-833199724c46","probe":"What is the title of section 24.0?","golden":"HOLDOVER","png_sha":"214b816ecbf747322726d54a0cb92edd6d184be6a6e04656e532d637c65eda11","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLD OVER"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLD OVER"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLD OVER"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLD OVER"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLD OVER"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLD OVER"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLD OVER"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLD OVER"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLD OVER"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"HOLDOVER"}]},{"eval_id":"019de200-d4c6-7729-866a-8ac3402457fb","probe":"What is the title of Article XIV?","golden":"Assignment and Subletting","png_sha":"d8fa233fb12db1beef1e4088d39215700d5884c2d4cb968b6985c6febde8a2ca","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Assignment and Subletting\""},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Assignment and Subletting"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ASSIGNMENT AND SUBLETTING"}]},{"eval_id":"019de200-d4c7-7305-82b7-76d4d75e7f9d","probe":"What is the title of Article XIII?","golden":"Condemnation","png_sha":"d8fa233fb12db1beef1e4088d39215700d5884c2d4cb968b6985c6febde8a2ca","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The title of Article XIII is \"Condemnation\"."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"ConDemnation"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The title of Article XIII is \"Condemnation\"."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Condemnation"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"CONDEMNATION"}]},{"eval_id":"019de200-d4c9-7b7f-9e32-c47d4f1c0b0e","probe":"What is the title of Exhibit D?","golden":"Form of Deed","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form of Deed"}]},{"eval_id":"019de200-d4ca-7805-9cc9-6e26cd367bbc","probe":"What is the title of Article 25?","golden":"Waiver of Jury Trial","png_sha":"c7b7da566d3062ed9a8ba02932fd59628e80cd8d631901d4f41c8c6b1fecb401","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Waiver of Jury Trial"}]},{"eval_id":"019de200-d4cd-7c1a-a4b1-fd5dc2875413","probe":"What is the title of section 24.4?","golden":"Captions","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Captions"}]},{"eval_id":"019de200-d4cf-7e95-8f4b-cca6ed5396ce","probe":"What is the title of section 24.5?","golden":"Severability","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Severability"}]},{"eval_id":"019de200-d4d0-7008-bd98-2d410f1fb7fa","probe":"What is the name of the person to contact for the Lessor in the notices section?","golden":"Mr. Juan Carlos Gonzalez Quezada","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. Juan Carlos Gonzalez Quezada"}]},{"eval_id":"019de200-d4d1-7e39-92cb-dc82b006e040","probe":"What is the title of section 24.1?","golden":"Brokers","png_sha":"1af6fa12ce14a289540338002d653fcf715cbdac9c109368f7a75e1831e9ebc3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers (Intentionally Omitted)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers, [Intentionally Omitted]"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers; [Intentionally Omitted]"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brokers"}]},{"eval_id":"019de200-d4d4-7185-bf69-9197f90e27ce","probe":"What is the title of Section II?","golden":"TENANT'S WORK","png_sha":"215e3357118390046b09fa453fde29d704da10672369a99113420e2a59b5865c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Tenant's Work"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"TENANT'S WORK"}]},{"eval_id":"019de200-d4da-740b-af0a-30cdbbdc3a00","probe":"What is the rent payable for July 2018?","golden":"145,763","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"}]},{"eval_id":"019de200-d4db-76f8-b9cf-eb901aaef607","probe":"What is the title of Exhibit N?","golden":"Exclusions From Operating Expenses","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions from Operating Expenses"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Exclusions From Operating Expenses"}]},{"eval_id":"019de200-d4de-7510-a1bb-a2200cf532b1","probe":"What is the rent payable for May 2018?","golden":"145,763","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"145,763"}]},{"eval_id":"019de200-d4e0-7497-8998-04b404a57589","probe":"What is listed as item (i) under Excluded Expenses in Exhibit N?","golden":"Real Estate Taxes","png_sha":"f4a1dca671f2b56d9522e729d99d107f4ed6e70b360bb81bc826a2a49d32209e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Real Estate Taxes"}]},{"eval_id":"019de200-d4e3-7937-8135-40c4b4f0cb8e","probe":"What is the markup percentage on outgoing mail?","golden":"10%","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10%"}]},{"eval_id":"019de200-d4e4-7765-86d5-d5fb371119ed","probe":"What is the title of Exhibit B?","golden":"Summit Billing Information","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summit Billing Information"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"SUMMIT BILLING INFORMATION"}]},{"eval_id":"019de200-d4e5-7bb2-9e8d-5d17eac142de","probe":"What is the reconnection fee per hour mentioned in Exhibit C?","golden":"$100","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour, 1/2 hour minimum"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour, 1/2 hour minimum"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour, 1/2 hour minimum"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour, 1/2 hour minimum"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour, 1/2 hour minimum"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour, 1/2 hour minimum"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour, 1/2 hour minimum"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour, 1/2 hour minimum"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour, 1/2 hour minimum"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100 per hour"}]},{"eval_id":"019de200-d4e6-7499-90b0-274586c057d5","probe":"What are the standard business hours listed for Summit's remedial maintenance?","golden":"9:00 am to 5:00 pm, Monday - Friday","png_sha":"1d8ba66687cea72d6ae46ad9ac7b635a6a94eb74326ec31f95a4e6d220ce16d3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday- Friday"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9:00 am to 5:00 pm, Monday - Friday"}]},{"eval_id":"019de200-d4e8-7f62-96ae-519b14f37f5f","probe":"On what day of December 2024 did the Guarantors execute this Guaranty?","golden":"13th","png_sha":"17421f00db7e68e09f420ba5abd403a8bc79b47f8f380327515bff5297f38fed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day of December, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th day of December, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"13th"}]},{"eval_id":"019de200-d4ea-7529-926e-f6d2957fdefe","probe":"Who is the Named Tenant?","golden":"2U Harkins Road LLC","png_sha":"53a810b9767d8b72ec62e5f926aafc2a4c92f6a0106a41f2b05ead9eec81cf6e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2U Harkins Road LLC"}]},{"eval_id":"019de200-d4ed-7a5a-bca1-903c35b0c671","probe":"What is the speed limit mentioned in rule 4 of the parking rules?","golden":"5 miles per hour","png_sha":"4a35d25bb27a032bf2661265ea4187cfc0129b1d6aa4a12ae16fc6380aea8e4c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5 miles per hour"}]},{"eval_id":"019de200-d4f5-78f3-8340-3580046edcc8","probe":"What is the each occurrence limit for Personal Injury Liability?","golden":"$9,000,000","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,000,000"}]},{"eval_id":"019de200-d4f6-7741-884c-42611e27bcef","probe":"What is the Insured's participation percentage for Personal Injury Liability?","golden":"0%","png_sha":"c5ea0ab478bba48e658378f71da344431d49c6f2a764fbd27b7204b6aa51a7ac","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"0%"}]},{"eval_id":"019de200-d4fa-70fc-b7a8-b9c26c2b14e0","probe":"By what date must Tenant substantially complete the 2nd Floor Build-Out Work?","golden":"April 1, 2018","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2018"}]},{"eval_id":"019de200-d4fb-7f01-8927-c6d175a34ace","probe":"By what date must Tenant substantially complete the Initial Build-Out Work of the Initial Premises?","golden":"April 1, 2017","png_sha":"c51aba7a96660ab0a7e88f6abc42d68f5f7f293a232d8303c532f7368f28dff6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"April 1, 2017"}]},{"eval_id":"019de200-d4fc-7cca-908f-984e3d8120e7","probe":"What is the umbrella liability each occurrence amount?","golden":"$5,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$5,000,000"}]},{"eval_id":"019de200-d4ff-7fd5-9027-7197160465a2","probe":"What is the automobile liability combined single limit amount?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"1,000,000\""},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d500-7cfe-8ff2-d8bbbb64073a","probe":"What is the bodily injury by accident coverage amount per accident under Workers' Compensation Coverage B?","golden":"$500,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$500,000"}]},{"eval_id":"019de200-d501-782d-845b-a4e35e143c20","probe":"What is the combined single limit per occurrence for Coverage A under Commercial General Liability?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d503-798a-afa1-45a2677f34db","probe":"What is the personal and advertising injury liability (Coverage B) amount?","golden":"$1,000,000","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,000,000"}]},{"eval_id":"019de200-d504-70ea-9d31-b199175fed3c","probe":"In what geographic area must business interruption insurance match amounts customarily carried by responsible tenants?","golden":"Greater Boston","png_sha":"95151c36ecc0b239c0ffdb5510644c1687bd60d04507d3bce0a3576b29e5ea01","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"the Greater Boston area\""},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"the Greater Boston area\""},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Greater Boston area"}]},{"eval_id":"019de200-d509-782f-8cb5-81249701c47f","probe":"What percentage of the excess must Tenant pay to Landlord as Assignment/Sublease Excess Rent?","golden":"100%","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"100%"}]},{"eval_id":"019de200-d50a-7a93-8a69-a34202f99ee3","probe":"What is the term used for the portion of Premises eliminated under the Elimination Period?","golden":"Eliminated Space","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The \"Eliminated Space\""},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Eliminated Space"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Eliminated Space\""}]},{"eval_id":"019de200-d50c-743d-ad76-780e2c2fb12d","probe":"What is the term used for the period after the Elimination Period during which the Eliminated Space is restored to the Premises?","golden":"Restoration Period","png_sha":"96b13edfecbca4b3a0150e95bc2092d9077a8659be2b8459a5dba335ce389669","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"Restoration Period\""},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The \"Restoration Period\""},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The \"Restoration Period\""},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The \"Restoration Period\""},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The \"Restoration Period\""},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The \"Restoration Period\""},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The \"Restoration Period\""},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The \"Restoration Period\""},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Restoration Period"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The \"Restoration Period\""},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Restoration Period"}]},{"eval_id":"019de200-d50f-730f-bba3-567d098ebd36","probe":"By what time each weekday must the stainless steel tops on the 18th Street light boxes be wiped down?","golden":"8:00 AM","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"by 8:00 AM"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"prior to 8:00 AM\""},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"By 8:00 AM each weekday."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"8:00 AM"}]},{"eval_id":"019de200-d510-7320-b95d-f545ed219bc5","probe":"How often must window frames and ledges be swept with a soft-bristled brush on the building exterior?","golden":"Monthly","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Monthly"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"monthly"}]},{"eval_id":"019de200-d512-7496-808b-5b1ea05ca3f8","probe":"How often must standpipe fire hose connections on the exterior of the building be cleaned and polished?","golden":"Weekly","png_sha":"642804342adf0bfa2aa2250063bb805e15d6af147ba5d32a381ba08adbbc88ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"WEEKLY"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"WEEKLY"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"WEEKLY"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"WEEKLY"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"WEEKLY"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"WEEKLY"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Weekly"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"weekly"}]},{"eval_id":"019de200-d513-7149-ae8c-e8a7754d572b","probe":"What is the minimum amount for a partial prepayment of Revolving Loans?","golden":"$100,000","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"}]},{"eval_id":"019de200-d519-76a9-b52e-17fb3cd3da08","probe":"What rate do Revolving Loans accrue interest at, plus the Applicable Margin?","golden":"LIBOR Rate","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The LIBOR Rate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"LIBOR Rate"}]},{"eval_id":"019de200-d51a-7cbd-841b-aa945ef2b4a8","probe":"Notices of Borrowing must be delivered before what time (Eastern time)?","golden":"1:00 p.m.","png_sha":"dea3e2590608136fd77389c93c724163508ff908a65663f9793a67f69cfadf7e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"\"1:00 p.m. (Eastern time)\""},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1:00 p.m."}]},{"eval_id":"019de200-d51b-7404-9feb-b6384f640f1a","probe":"How many calendar days prior to lease termination must the parties allow Lessor to enter the property for inspection?","golden":"60","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sixty (60)"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"60"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60) calendar days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"sixty (60)"}]},{"eval_id":"019de200-d51c-7dd7-ad07-e2fd96baf505","probe":"Who conducted the Phase I Environmental Assessment mentioned in section 11.1?","golden":"GAIM REGIOMONTANA","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GAIM REGIOMONTANA"}]},{"eval_id":"019de200-d51e-7caf-b475-352d47499736","probe":"What is the postal code (C.P.) listed in the address for Mr. Juan Carlos Gonzalez Quezada?","golden":"66220","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66220"}]},{"eval_id":"019de200-d520-7d78-a11e-ce881c0ff357","probe":"How many calendar days does Lessor have to object to a proposed sublease in writing?","golden":"30","png_sha":"68c673ffd42fb6d91d22d4f9a1c15120709f2cf57b017949f5efe8ba60b0b8ed","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30)"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 calendar days"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30)"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30 calendar days"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30)"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"30"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30)"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30)"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30)"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"thirty (30) calendar days"}]},{"eval_id":"019de22d-8775-7482-9f31-5e7710938d70","probe":"What is the original principal amount of the 3.50% Series A Convertible Senior Notes due February 1, 2018?","golden":"$70.3 million","png_sha":"9999d442e3243c2ea48a7de6c4c9b162568b4e59e41492087837bdb419a11d2c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$70.3 million"}]},{"eval_id":"019dfae7-e8c3-7289-a5e3-25d26a497795","probe":"What is the fiscal year end date?","golden":"September 28, 2024","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 28, 2024"}]},{"eval_id":"019dfae8-2c75-7590-9083-4c07bf26944a","probe":"What is the Commission File Number?","golden":"001-36743","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-36743"}]},{"eval_id":"019dfae8-8300-75b0-98f0-558c886fd068","probe":"What is the registrant's telephone number?","golden":"(408) 996-1010","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(408) 996-1010"}]},{"eval_id":"019dfae8-d37e-73db-bad0-7dbbebba1d87","probe":"What is the IRS Employer Identification Number?","golden":"94-2404110","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"94-2404110"}]},{"eval_id":"019dfae9-3119-7c26-b2ed-73fb2888fdfe","probe":"What is the par value per share of Apple's common stock?","golden":"$0.00001","png_sha":"eac06851b3a30167de75750e9e11539210e98c056ea59506ee6049194309bce2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.00001"}]},{"eval_id":"019dfaea-1b4b-7bef-bf30-f8f1ee1cb9d6","probe":"What were Europe net sales in 2024 (in millions)?","golden":"$101,328","png_sha":"9a0e251058123efabc1b1e90748d363c92e021ed12de1fff8bfd537eb10334cf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"101,328"}]},{"eval_id":"019dfaec-3d80-7c7c-95b7-6a34a086d48b","probe":"What is the date the report was signed?","golden":"November 1, 2024","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 1, 2024"}]},{"eval_id":"019dfaec-8345-7eea-8840-6867945a7a06","probe":"Who is the Director and Chair of the Board?","golden":"Arthur D. Levinson","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Arthur D. Levinson"}]},{"eval_id":"019dfaec-e961-7051-a4ce-b66996997cb2","probe":"Who is the Senior Director of Corporate Accounting?","golden":"Chris Kondo","png_sha":"5146ef4751c2c2c1de7a0c504467b5cd9406df20cabc1ab6871c6b4e62e474be","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Chris Kondo"}]},{"eval_id":"019dfaed-c27e-7590-9034-1cc2a5319b55","probe":"Who is the accounting firm that signed this consent?","golden":"Ernst & Young LLP","png_sha":"2aaf645d8ab89843415b953bc9434e952d5937b41b7443fa8dd027706987d91c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ernst & Young LLP"}]},{"eval_id":"019dfaf0-11d2-70d1-be50-371940478750","probe":"Where is Braeburn Capital, Inc. incorporated?","golden":"Nevada, U.S.","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nevada, U.S."}]},{"eval_id":"019dfaf0-52d8-7941-b336-19bfbe7f8bc1","probe":"Where is Apple Asia Limited incorporated?","golden":"Hong Kong","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hong Kong"}]},{"eval_id":"019dfaf1-05a1-718d-818a-e45ba4945ba1","probe":"Where is Apple Operations Mexico, S.A. de C.V. incorporated?","golden":"Mexico","png_sha":"28f7a10fe8e5ac029578144cb0447b016116c894d1f16447a62ce2880ca0a2ff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mexico"}]},{"eval_id":"019dfaf2-2642-7eae-b1fb-1620be9706bc","probe":"Starting on what date does this policy apply to Incentive-Based Compensation that is Received?","golden":"October 2, 2023","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 2, 2023"}]},{"eval_id":"019dfaf3-d93a-7e7a-8293-bed401dc3c74","probe":"Under what year's Securities and Exchange Act is 'executive officer' defined for this policy?","golden":"1934","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1934"}]},{"eval_id":"019dfaf4-6d06-7bb4-9da0-5703eced16ad","probe":"What company's logo appears at the top of this policy?","golden":"Apple","png_sha":"47756f29d559d9381c130714e1a4ea90c042cd9632df0fe4ce2209c62a5c0218","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Apple"}]},{"eval_id":"019dfaf5-67bd-727d-92f0-43a3108e55cf","probe":"What is the commission file number?","golden":"001-37580","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"001-37580"}]},{"eval_id":"019dfaf5-e414-73d4-a5bb-864069d83389","probe":"What is the IRS Employer Identification Number?","golden":"61-1767919","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"61-1767919"}]},{"eval_id":"019dfaf6-3c67-7437-b33f-106a71df96cc","probe":"What is the registrant's telephone number?","golden":"(650) 253-0000","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"(650) 253-0000"}]},{"eval_id":"019dfaf6-8eaf-75f8-a68a-e019cf9ab6dc","probe":"What is the interest rate of the Senior Notes due 2064?","golden":"4.375%","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.375%"}]},{"eval_id":"019dfaf6-cd98-71f2-9576-0e07833ebd70","probe":"What is the interest rate of the Senior Notes due 2028?","golden":"2.375%","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.375%"}]},{"eval_id":"019dfaf7-7376-72e6-af9f-4f0302bf05aa","probe":"What is the trading symbol for Alphabet's Class C Capital Stock?","golden":"GOOG","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** GOOG\n**"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"GOOG"}]},{"eval_id":"019dfaf7-a3e9-7079-abc1-1170e6a73c4f","probe":"What is the fiscal year end date on this 10-K?","golden":"December 31, 2025","png_sha":"877e278705378e25cb29edd2811b664e7d1c3caa83316e3533ab4dbf6dfebc9e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"}]},{"eval_id":"019dfaf8-f7e3-7fa2-809d-07b2ec3cfaea","probe":"How much remained available for Class A and Class C share repurchases as of March 31, 2025?","golden":"$29.5 billion","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$29.5 billion"}]},{"eval_id":"019dfafa-9cb0-7412-8eac-d16591d94510","probe":"What is the quarterly cash dividend declared on April 2025?","golden":"$0.21","png_sha":"d19ecff948298570be802f5448bb11e72f9e397915f409b44b865645cca7afb7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$0.21"}]},{"eval_id":"019dfafd-0e8d-7a0f-8f4e-4d3d489b698a","probe":"By what percentage did the Board of Directors increase the quarterly cash dividend in April 2025?","golden":"5%","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5%"}]},{"eval_id":"019dfafe-5a0c-7b21-8bfa-72a257476e5a","probe":"What was the total carrying value of senior unsecured notes outstanding as of September 30, 2025?","golden":"$23.6 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.6 billion"}]},{"eval_id":"019dfaff-051e-7ba2-8350-09ebbfdb115a","probe":"How much remained available for Class A and Class C share repurchases as of September 30, 2025?","golden":"$74.8 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$74.8 billion"}]},{"eval_id":"019dfb00-8129-7fae-9c3d-085f17af7163","probe":"How many Class C shares were repurchased in the three months ended September 30, 2025 (in millions)?","golden":"51","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"51"}]},{"eval_id":"019dfb01-6670-7c43-bf57-578d4e8743df","probe":"How much was the revolving credit facility expiring in April 2030?","golden":"$6.0 billion","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$6.0 billion"}]},{"eval_id":"019dfb02-8211-7651-9ec4-8c0ebcf58a3b","probe":"What was the dollar amount of Class A share repurchases for the three months ended September 30, 2025 (in millions)?","golden":"$926","png_sha":"3a3be8e214b4bbddfa4e3eb25fc0e36d226e224c29e2b1f5d40d3868d988c6c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$926 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"926"}]},{"eval_id":"019dfb06-2d63-7e40-9cfc-442adddd3a61","probe":"As of what date did the CEO and CFO conclude on the disclosure controls evaluation?","golden":"June 30, 2025","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"}]},{"eval_id":"019dfb06-7255-7580-9ef1-58f24ae75626","probe":"What rule under the Exchange Act was used to evaluate disclosure controls and procedures?","golden":"Rule 13a-15","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rule 13a-15"}]},{"eval_id":"019dfb07-58e1-741b-95ae-39f6ad5b9738","probe":"For what quarter ended date is the internal control reporting statement made?","golden":"June 30, 2025","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2025"}]},{"eval_id":"019dfb08-723b-72c9-8209-4c6b104c74d9","probe":"What form is the Quarterly Report on?","golden":"Form 10-Q","png_sha":"67b47cecb1f939a21e4f89b7aa742205986fc1b1bb021c88bfc69f2101c23bd9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Form 10-Q"}]},{"eval_id":"019dfb09-b2b4-7900-94d0-5ead62b5fa3a","probe":"How much was the initial investment used in the graph comparison?","golden":"$100","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"}]},{"eval_id":"019dfb0a-1542-7607-afff-3824643328be","probe":"On what date does the graph's tracking period end?","golden":"December 31, 2025","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2025"}]},{"eval_id":"019dfb0a-4250-7161-8e90-fa2502ad8254","probe":"What is the starting date of the graph's tracking period?","golden":"December 31, 2020","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"December 31, 2020"}]},{"eval_id":"019dfb0a-bbec-7b6d-bb26-274ff05f9459","probe":"What is the highest dollar value shown on the y-axis of the graph?","golden":"$400","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$400"}]},{"eval_id":"019dfb0a-e54b-7973-8d05-99144d938deb","probe":"What color is the line representing the S&P 500 in the graph?","golden":"Green","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"green"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Green"}]},{"eval_id":"019dfb0b-0fe9-717a-b315-903647d9114e","probe":"What color is the line representing Alphabet Inc. Class C in the graph?","golden":"Red","png_sha":"6ff4691a4cd91be0f638d2eebe53ef994a33bc521fcca9feba329f225a3d2563","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"red"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"}]},{"eval_id":"019dfb0b-9664-7b20-bea5-647276953368","probe":"How much is Alphabet acquiring Wiz, Inc. for?","golden":"$32.0 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$32.0 billion"}]},{"eval_id":"019dfb0c-07a8-768c-bf46-7d82769ad116","probe":"What is the long-term income taxes payable as of December 31, 2025?","golden":"$9.5 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9.5 billion"}]},{"eval_id":"019dfb0d-98a6-7573-8987-ba32c57f6b7a","probe":"What is the total amount of purchase commitments and other contractual obligations as of December 31, 2025?","golden":"$149.1 billion","png_sha":"8e83d64c9af79f8098697a5e59ade53e01cdc3564cd1368a8d10d4852115df32","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$149.1 billion"}]},{"eval_id":"019dfb14-6817-7cc7-90e2-fce76cd476e7","probe":"How many employees did JPMorganChase have globally as of December 31, 2025?","golden":"318,512","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"318,512"}]},{"eval_id":"019dfb14-a085-7b52-8f76-6678f2a4de9c","probe":"How many employees does JPMorganChase have in North America?","golden":"185,208","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"185,208"}]},{"eval_id":"019dfb14-f2e3-7cee-a27e-79e81867b37a","probe":"How many employees work in CCB?","golden":"144,196","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"144,196"}]},{"eval_id":"019dfb15-3908-7fc5-93bd-052705ae9929","probe":"In how many countries are JPMorganChase's employees located?","golden":"66","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 countries"}]},{"eval_id":"019dfb15-75a7-7c29-a2ca-90c32df63ac5","probe":"What percentage of total employees are women?","golden":"48%","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48%"}]},{"eval_id":"019dfb15-c7c7-74ee-b29b-e7b5d8c9a152","probe":"How many employees work in the Asia-Pacific region?","golden":"96,499","png_sha":"c219383aa17b6aa4c1ad0ad27b31ee898099581be889b4234de29de9cdb18bea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"96,499"}]},{"eval_id":"019dfb16-cbe3-7d4d-a23d-2234c2d7d297","probe":"What is the first bulleted item under the list of electronic and internet-based financial solutions?","golden":"lending and other extensions of credit to consumers","png_sha":"704943f48019c6bab8cb509e1ddeb6f9b48085007ac9101976ed3d04798ac274","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lending and other extensions of credit to consumers"}]},{"eval_id":"019dfb17-0cc4-74a1-8d62-afab29ef1e82","probe":"What is the third bulleted item under the list of electronic and internet-based financial solutions?","golden":"cryptocurrency, including stablecoins","png_sha":"704943f48019c6bab8cb509e1ddeb6f9b48085007ac9101976ed3d04798ac274","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"cryptocurrency, including stablecoins"}]},{"eval_id":"019dfb1a-7fed-744e-a7bc-585de30578fb","probe":"What was the equity assets value in 2025 (in billions)?","golden":"$1,400","png_sha":"ad9015638aac25f82a20ba49bfd486496703e99331d9f376ff62501507f0c7ab","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1400 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1400 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1,400"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,400 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1400 billion"}]},{"eval_id":"019dfb1a-d4b4-7ee1-b950-3f3208c24be4","probe":"What was the reported net interest income in 2025 (in millions)?","golden":"$95,443","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 95,443"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$95,443"}]},{"eval_id":"019dfb1b-4a0a-766a-92cd-c2e37df27c36","probe":"What was the net yield on average interest-earning assets on a managed basis in 2025?","golden":"2.50%","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%\nEVIDENCE \"Net yield on average interest-earning assets - managed basis\""},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.50%"}]},{"eval_id":"019dfb1b-9e1c-704c-b958-e7a06540c65f","probe":"What was the Memo: Total Markets net revenue in 2025 (in millions)?","golden":"$35,782","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35782"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35,782"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35,782"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35,782"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"35,782"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$35,782"}]},{"eval_id":"019dfb1c-4c58-739f-8241-e4a688fff415","probe":"What was the noninterest revenue excluding Markets in 2023 (in millions)?","golden":"$44,361","png_sha":"32754cbea0a045f0e8fb10397e6320f667d3b093ea2086c90eeec51712bfe8fe","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$44,361"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"44,361"}]},{"eval_id":"019dfb1d-0b1b-7540-9211-41f0ac069d15","probe":"In what year was MetLife, Inc. incorporated in Delaware?","golden":"1999","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"1999"}]},{"eval_id":"019dfb1e-4042-7d24-95d6-9213cb5fb946","probe":"How many factors are listed on this page?","golden":"22","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22"}]},{"eval_id":"019dfb1e-d54d-73fd-8f17-16eb21390c86","probe":"What is factor number 10 in the list?","golden":"London Interbank Offered Rate discontinuation and transition to alternative reference rates","png_sha":"a88ad41041db200a2174a9acc163961c7f2364800971d8de2683983e6b25245a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"London Interbank Offered Rate discontinuation and transition to alternative reference rates"}]},{"eval_id":"019dfb1f-5f66-79ad-be34-3c4e429dbcac","probe":"How old is Steven J. Goulart?","golden":"64","png_sha":"8a8df5c53ffc88bd982b700c7adc729d6f1a78da7ebcbf1ee0a1a778e2017590","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64"}]},{"eval_id":"019dfb22-1d21-7795-bb3e-bdc661245cb9","probe":"What is the % of Total for Aaa/Aa/A rated securities as of December 31, 2021?","golden":"70.4%","png_sha":"cbb17b332fbfca22950517f9180fc39ec5eda902185cb538029062299369bf22","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"70.4 %"}]},{"eval_id":"019dfb23-8371-717a-825f-6e20e45dcb5f","probe":"What is the U.S. segment's percentage contribution to total segment level adjusted earnings?","golden":"47%","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47%"}]},{"eval_id":"019dfb23-d976-764b-875f-1c7d8d24b80e","probe":"What were the adjusted earnings for the Asia segment?","golden":"$1,378 million","png_sha":"bcc51fb1b360835507e532a16a234315479af4d9b1394b856984bb00f57262d8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$1,378 million"}]},{"eval_id":"019dfb29-7d6d-77ed-abe1-9e196503fe98","probe":"What is American Life Insurance Company's Moody's rating?","golden":"A1","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1, 5th of 21"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A1"}]},{"eval_id":"019dfb29-d233-7190-9c54-414c50184509","probe":"What is Metropolitan Life Insurance Company's Fitch rating?","golden":"AA-","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"AA-"}]},{"eval_id":"019dfb2a-30eb-73bc-9534-9a1a79fcefd9","probe":"What is Metropolitan Tower Life Insurance Company's Moody's rating?","golden":"Aa3","png_sha":"a50e3d737b50a026c2207832797733a0854cbdf6447d8fc9c7080f3eaf03bed9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aa3"}]},{"eval_id":"019dfb3c-0056-7fd4-8497-80ad7e52deed","probe":"What is the date on the letter?","golden":"September 12, 2025","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 12, 2025"}]},{"eval_id":"019dfb3c-443c-749d-9922-e22f48da574a","probe":"What is the total amount of expenses stated in the letter?","golden":"$537.6 billion","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$537.6 billion"}]},{"eval_id":"019dfb3c-e409-7e70-93e0-584a7b66e218","probe":"What is the fax number listed at the bottom of the letter?","golden":"916.322.4404","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"916.322.4404"}]},{"eval_id":"019dfb41-090f-742c-a295-a841b0d40942","probe":"What is the last year the ACFR publication target date in March was achieved, according to the letter?","golden":"2018","png_sha":"51b4b22b5d4f48b1d78224c8b61b5e65f78b7c2534c16dbb330743eff1fa1a0f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2018"}]},{"eval_id":"019dfb42-0697-72fe-ace9-658c5975fe72","probe":"What is the General fund balance as previously reported on 6/30/2023?","golden":"$64,003,688","png_sha":"4d385e9f1f0ded0edf6cd42e1fce98d308714a9c9a90264d60830da6a87b20a5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"64,003,688"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$64,003,688"}]},{"eval_id":"019dfb48-c7e6-72a9-8f31-8e936894de0c","probe":"What was the total primary government net position in 2006 (in thousands)?","golden":"$48,552,143","png_sha":"6ded8b72d8724efb0a5addcabb85b9fb055c8702b034b32a8bd9d35ae7b3b2d4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48,552,143"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 48,552,143"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$48,552,143"}]},{"eval_id":"019dfb49-36d0-787d-9b10-263d0dc86158","probe":"What was the total business-type activities net position in 2005 (in thousands)?","golden":"$9,638,143","png_sha":"6ded8b72d8724efb0a5addcabb85b9fb055c8702b034b32a8bd9d35ae7b3b2d4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 9,638,143"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$9,638,143"}]},{"eval_id":"019dfb49-c621-751e-8311-221426895f61","probe":"What date does the fiscal year end?","golden":"June 30, 2013","png_sha":"e78f4e20277a031b7f8a1c8ec01e35359d5db802026c772a280aa46b2e15036d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"June 30, 2013"}]},{"eval_id":"019dfb4a-c5b5-77b8-8666-73fe5ecf7295","probe":"What word appears on the banner above the figure in the seal?","golden":"EUREKA","png_sha":"e78f4e20277a031b7f8a1c8ec01e35359d5db802026c772a280aa46b2e15036d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"EUREKA"}]},{"eval_id":"019dfb4c-a89f-7747-8ca3-fb374afbe129","probe":"How many employees were in the Services industry in 2012?","golden":"6,219,000","png_sha":"ee102138e4471a718761ff29297490e756f20be442c4eab71f74ad7b88ef9337","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6,219,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"6219000"}]},{"eval_id":"019dfff9-bbf0-7f8f-9eeb-4283d498732d","probe":"What is the General Fund amount due from primary government to University of California?","golden":"$169,215","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$169,215"}]},{"eval_id":"019dfffa-9fa6-7a63-a87b-53eda9047796","probe":"What is the amount from Nonmajor governmental funds due to University of California?","golden":"36,988","png_sha":"5b6c11a3eaa9199c3202b200409ff035721076a5066775d38ddc5d742a603be6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$36,988"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$36,988"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$36,988"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$36,988"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$36,988"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$36,988"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$36,988"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"36,988"}]},{"eval_id":"019dfffb-b244-7a37-903d-2e6addf12282","probe":"What was the net general bonded debt per capita in 2018?","golden":"$2,042","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2042"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,042"}]},{"eval_id":"019dfffc-0d62-7f14-a566-4e70db84b399","probe":"What was the net general bonded debt as a percentage of personal income in 2015?","golden":"4.0%","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4.0%"}]},{"eval_id":"019dfffc-678a-79c5-aaea-473c3f22a054","probe":"What was the General obligation bonds amount in 2017?","golden":"$79,503,871","png_sha":"d6db010462ed04cf30d87e82024a5910e860973024f9b76549b579b87baa4aa8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 79,503,871"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$79,503,871"}]},{"eval_id":"019dfffc-e4bf-79ad-8c4e-89d704ac54ed","probe":"What is at the top of the Texas government structure chart?","golden":"The Electorate","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Electorate"}]},{"eval_id":"019dfffd-a1d4-7a49-94b8-3ef9aa5497d4","probe":"What are the two highest courts shown under the Judicial branch?","golden":"The Supreme Court of Texas and The Court of Criminal Appeals","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Supreme Court of Texas and The Court of Criminal Appeals"}]},{"eval_id":"019dfffe-6b06-706f-a135-e5934397dcc8","probe":"What body sits directly below the Legislature on the chart, alongside the State Auditor's Office?","golden":"Legislative Committees","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Legislative Committees"}]},{"eval_id":"019dffff-a90b-7567-a8fa-d73e11996c14","probe":"What body is shown at the very bottom of the Legislative branch chart?","golden":"Sunset Advisory Commission","png_sha":"cbbae8f5a500af86d58bd402ded850a9aeb85663b11dfb71ea727de1bf5cbdfa","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sunset Advisory Commission"}]},{"eval_id":"019e0000-52c3-755e-9a98-534e00107784","probe":"What is the total pass-through to other agencies?","golden":"$254,334.30","png_sha":"cee789f33becc6e55d762115a7b119808f36099b5c736f4b0ec740bce52a004c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$254,334.30"}]},{"eval_id":"019e0001-dddd-7fec-b736-f93ff293500f","probe":"What was the balance in the ESF fund on Aug. 31, 2024?","golden":"$23.8 billion","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$23.8 billion"}]},{"eval_id":"019e0003-4dd3-73ec-8ba4-bf652587ad06","probe":"By how much is Texas' population projected to grow in 2025?","golden":"376,600","png_sha":"ade3f8b3d508786dd484fba0c013083e2f1282727fd9f3e639ee21b826e7ad9a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"376,600"}]},{"eval_id":"019e0008-27fa-70f4-8421-41777f7bcace","probe":"What office is shown in pink under the First Deputy Mayor?","golden":"Office of Efficiency","png_sha":"0280a69eb0eaa22d41121428d855c8cab9d9ef279e59078102092b5746f79e70","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The Office of Efficiency"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Office of Efficiency"}]},{"eval_id":"019e0009-2f8e-768d-8762-ff9e82bcea2b","probe":"What is the SAO Report Number?","golden":"25-316","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25-316"}]},{"eval_id":"019e0009-af38-766a-9ac7-cb0908ad2999","probe":"What percent of the assets of the Colleges and Universities does the University of Texas System constitute?","golden":"72.9 percent","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"72.9 percent"}]},{"eval_id":"019e000a-7052-7138-b0db-733f874d02cd","probe":"What percent of the expenditures for the State Highway Fund does the Texas Department of Transportation constitute?","golden":"99.9 percent","png_sha":"f9f4616ef3e18f2333f50f0c467f2af527952c53c495ad12ab1a7edb40e06ef7","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"99.9 percent"}]},{"eval_id":"019e000b-d49b-7660-82c4-81ecfb04a236","probe":"What percentage of revenue comes from Charges for Services in Graph MDA-6?","golden":"59.7%","png_sha":"3f8e2c78a2134ddb79f740cc731c989a29e5b11d89cdb0254e1f1740d44cfdb0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.7%"}]},{"eval_id":"019e000d-e61a-7a45-b84f-1c881c74e271","probe":"What is the fair value of Private Equity investments (in thousands)?","golden":"$76,309,756","png_sha":"1993d56fb3f7471f5844aa6a62bb8dd9a43b4784dac30f107664bca458bf68ea","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76309756"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$76,309,756"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"76,309,756"}]},{"eval_id":"019e0010-c825-72aa-a139-0e4ab295b2dc","probe":"What is the minimum aggregate floor area required by the CEP program?","golden":"25,000 square feet","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"25,000 square feet"}]},{"eval_id":"019e0011-2a92-7ac7-89be-ac4f2296baea","probe":"Under the CRP/CEP programs, by how much were the City's tax revenues reduced in 2024 (in thousands)?","golden":"$12,500","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,500"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,500"}]},{"eval_id":"019e0011-cff1-7126-8235-02b26f0fbab9","probe":"What year did ICAP replace ICIP?","golden":"2008","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2008"}]},{"eval_id":"019e0017-450f-737d-a346-38c48007c835","probe":"Under the CRP program, what is the per-square-foot dollar amount used in the base abatement calculation formula?","golden":"$2.50","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50 per sq. ft."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2.50"}]},{"eval_id":"019e0018-17a0-7847-a0b3-11f039bc48a6","probe":"What is the page number shown at the bottom of this page?","golden":"128","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128"}]},{"eval_id":"019e0019-d170-7146-8e38-cc44276e6018","probe":"Under the CRP/CEP programs, by how much were the City's tax revenues reduced as a result of abatement agreement in 2024 (in thousands)?","golden":"$12,500","png_sha":"7371f09be440c1209ee0316b99cdec92766ea0201ca794a0776e3f10a392556e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,500"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,500"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,500"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12,500"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$12,500"}]},{"eval_id":"019e001b-3183-79f1-a745-4e066a6ce3ef","probe":"What is the Executive Order number mentioned in the letter?","golden":"2025-1","png_sha":"781c6fcbd4f3164179bf71cd942ca2e9794fc7c49c6bbcf883dd13f2ce626331","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Executive Order 2025-1"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Executive Order 2025-1"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Executive Order 2025-1"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Executive Order 2025-1"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Executive Order 2025-1"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Executive Order 2025-1"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Executive Order 2025-1"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Executive Order 2025-1"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Executive Order 2025-1"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025-1"}]},{"eval_id":"019e001d-d405-7881-ab8b-abcb0d7e70e1","probe":"What is Deloitte's fax number listed on the page?","golden":"+1 312 486 1486","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"+1 312 486 1486"}]},{"eval_id":"019e001f-f83d-78ad-bad5-21b87bdb9833","probe":"According to the auditor's report, the Pension Trust Funds represent what percentages of the assets, financial position, and revenues respectively?","golden":"92%, 100%, and 72%","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"92%, 100%, and 72%"}]},{"eval_id":"019e0020-bffb-7733-931f-63dac6e0f8f0","probe":"Who is the report addressed to as Mayor?","golden":"Brandon Johnson","png_sha":"76f3f3803c688cfb5d5f08e433fd7e76a465728d57de04023c947fbf7fbed7a2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Brandon Johnson"}]},{"eval_id":"019e0027-f41a-7a7a-b3f6-f9b59cde341b","probe":"What is the experience study period for the Policemen's plan?","golden":"January 1, 2019 - December 31, 2023","png_sha":"2aded5f520cbaa023e8d0c1e94f15e68ccafa9f34d1e6736781e6f894512fe8e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2019 - December 31, 2023"}]},{"eval_id":"019e0028-b45f-7292-959c-f04db8d08d19","probe":"What is the experience study period for the Laborers' plan?","golden":"January 1, 2017 - December 31, 2019","png_sha":"2aded5f520cbaa023e8d0c1e94f15e68ccafa9f34d1e6736781e6f894512fe8e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 1, 2017 - December 31, 2019"}]},{"eval_id":"019e002e-ef48-7527-8160-cb77c6e44245","probe":"On what date did the City of Chicago City Council adopt the ordinance organizing the STSC?","golden":"October 11, 2017","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"October 11, 2017"}]},{"eval_id":"019e0030-d1da-7720-bec1-d70663e3456a","probe":"On what date did the City Council adopt the CCCF Ordinance?","golden":"November 16, 2016","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"November 16, 2016"}]},{"eval_id":"019e0033-8f40-79d7-8505-50112ded8060","probe":"What is the website where complete financial statements of the STSC can be obtained?","golden":"www.salestaxsecuritizationcorporation.com","png_sha":"47b90d435b8c7e012c071a9d21499331bc410f39993229d2712628ca8a6b899a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"www.salestaxsecuritizationcorporation.com"}]},{"eval_id":"019e003a-5da3-7d08-9f15-665248ccb0cf","probe":"What was the final budgeted Vehicle Tax amount under Transportation Tax (in thousands)?","golden":"$128,777","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$128,777"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"128,777"}]},{"eval_id":"019e003a-e619-7c9f-b4b2-aa2807d3bff9","probe":"What was the actual Motor Fuel Tax and Project revenue under Transportation Tax (in thousands)?","golden":"$122,483","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"122,483"}]},{"eval_id":"019e003c-6cc9-782c-bca0-875bef94c76c","probe":"What was the final budgeted MEABF Pension Reserve under Special Area and Utility Taxes (in thousands)?","golden":"$216,275","png_sha":"d27c2c3fe29477d311cf8fb9c70e7f48272db3f244363cf5a60c5872e6561e7f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"216,275"}]},{"eval_id":"019e003d-55d2-7007-b3b6-dc37892643d2","probe":"Who is the Chief Actuary?","golden":"Marek Tyszkiewicz","png_sha":"89c77daf9c6f881f0116f445cbf736cffc12698b60a93b437699a1a075b00138","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marek Tyszkiewicz"}]},{"eval_id":"019e003f-44df-7a8d-a15c-ff2dc3cf553b","probe":"What is the funded ratio for the 2022 valuation date?","golden":"85.1%","png_sha":"13c08f8d02fa78d2fc1f1b9783d494af4a43f3083f75509ffac06a9ae415320f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"85.1%"}]},{"eval_id":"019e0040-0266-795a-b6d2-549f195f8032","probe":"What percentage of the Police Superior Officers' Variable Supplements Fund is held in Collective Trust Funds?","golden":"59.28%","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"59.28%"}]},{"eval_id":"019e0040-6668-7abd-8cd8-dd05d069c1c1","probe":"What is the dollar amount of Equity Securities in the Police Officers' Variable Supplements Fund?","golden":"$771,119","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"771,119"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$771,119"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"771,119"}]},{"eval_id":"019e0041-2237-71d4-8880-cb8564c7b0ae","probe":"What is the dollar amount of Short-Term Investments in the Police Superior Officers' Variable Supplements Fund?","golden":"$8,441","png_sha":"1c13a5b6d1c9f1294ee8e0c93206c8af6a217af1a1a7f95cb16cc965e1758b3b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$8,441"}]},{"eval_id":"019e0042-1c07-71d9-8683-e990abab4862","probe":"What is the Reduced Service Retirement probability at 20 years of service?","golden":"5.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"}]},{"eval_id":"019e0043-db39-746e-8a90-d9b8e9e16e2f","probe":"What is the Unreduced Before Full Escalation probability at 22 years of service?","golden":"5.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5.00%"}]},{"eval_id":"019e0044-11fe-7039-99f0-4014e1cca342","probe":"What is the Reduced Service Retirement probability at 21 years of service?","golden":"2.00%","png_sha":"8e61784b1d8eb46f49f5ae30d053e12f8a36ce621a76eba679dd983810c8d17d","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2.00%"}]},{"eval_id":"019e0048-5d8d-7e41-bfac-807538f6bc7d","probe":"What is the required year of adoption for GASB Statement No. 102?","golden":"2025","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2025"}]},{"eval_id":"019e004a-3183-7f93-ae28-888547cf9f69","probe":"What is the As Previously Stated Accrued and Other Liabilities amount (in thousands)?","golden":"$2,037,352","png_sha":"492e21fc695ab2c841cf09c0708ed2b87a794453d0a715d70c558854605322e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2,037,352"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$2,037,352"}]},{"eval_id":"019e004b-c349-7e93-af8d-24a8c0227413","probe":"Who is the Chairman of the Texas Transportation Commission?","golden":"J. Bruce Bugg, Jr.","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"J. Bruce Bugg, Jr."}]},{"eval_id":"019e004c-1788-7c26-832d-effce8fee9e9","probe":"What city is Commissioner Robert C. Vaughn from?","golden":"Dallas","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Dallas"}]},{"eval_id":"019e004c-7b29-737b-b3c2-4cb5677b686a","probe":"What city is Commissioner Steven D. Alvis from?","golden":"Houston","png_sha":"1e50379458f51768c0b177d3963bc9a801ecc24130bda95e1900b91f1e279dc0","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston\nEVIDENCE \"Commissioner Houston\""},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Houston"}]},{"eval_id":"019e004f-570b-7494-b4dc-1980043719cb","probe":"What is the Component Units amount for Uninsured and Uncollateralized in Table 3A (in thousands)?","golden":"$729,847","png_sha":"14dd94971a85d5333d42a72d87ae42c4f4cf19684f10114f6d12e3dc0dcfbba3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847\nEVIDENCE \"Component Units $ 729,847\""},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"729,847"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$729,847"}]},{"eval_id":"019e0050-7b43-7b4a-b132-8ba0d44ecc08","probe":"What is the Total Fund Balance \u2013 Governmental Funds (in thousands)?","golden":"$98,174,085","png_sha":"2e5b15b0fe9ca40f66bc4f99fea40f7e0fb26c9abe4ac75ea6dad2ab72ae36d6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** $ 98,174,085\n**"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 98,174,085"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 98,174,085"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$98,174,085"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$ 98,174,085"}]},{"eval_id":"019e007c-e48c-710f-9404-90a2a810ccb4","probe":"What is the Net Position of Governmental Activities (in thousands)?","golden":"$134,878,410","png_sha":"2e5b15b0fe9ca40f66bc4f99fea40f7e0fb26c9abe4ac75ea6dad2ab72ae36d6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134,878,410"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134,878,410"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$134,878,410"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"134,878,410"}]},{"eval_id":"019e007d-9a24-752a-89d4-7fe852700caa","probe":"What is the total revenue shown in the Revenue by Source pie chart?","golden":"$190.5 Billion","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Total = $190.5 Billion"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$190.5 Billion"}]},{"eval_id":"019e007e-1a80-7e4b-98c2-9c3f2d812c06","probe":"What percentage of revenue came from Taxes?","golden":"42.7%","png_sha":"cf71c70804d5518942eab54e2403246db177a77426fd0a8f0d96ac4c001c4e42","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"42.7%"}]},{"eval_id":"019e007f-3589-7306-b64b-6253528585e4","probe":"What page is Risk Factors on?","golden":"14","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"14"}]},{"eval_id":"019e007f-7683-7d10-a251-ff6bdde0aca0","probe":"What page is Executive Compensation on?","golden":"105","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"105"}]},{"eval_id":"019e007f-b345-710c-b63d-5812e55e82ef","probe":"What page is Financial Statements and Supplementary Data on?","golden":"48","png_sha":"7b334f9f1a36e48730307e82605ccb0951c6641286cdd4e19af9113b3a6d76a9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"48"}]},{"eval_id":"019e0080-81ba-7bac-bba1-8cc2e8324436","probe":"What page is the Budgetary Comparison \u2013 General Fund on?","golden":"47","png_sha":"0a460adc7db810670c579dc36d27c02a4097bb3e02f77fbbeacd84bbcc9d2f0e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"47"}]},{"eval_id":"019e0080-b0bf-7f30-a02e-a2ed8dcea371","probe":"What page is the Schedule of Employee Benefits \u2013 All Funds on?","golden":"56","png_sha":"0a460adc7db810670c579dc36d27c02a4097bb3e02f77fbbeacd84bbcc9d2f0e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56\nEVIDENCE \"Schedule of Employee Benefits \u2013 All Funds 56\""},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"56"}]},{"eval_id":"019e0081-ed0a-7c3a-a9ba-53b6b5920008","probe":"What word is shown as a watermark across the map?","golden":"DRAFT","png_sha":"5a6ce9b2db24bcdcf202f3778295d7d1ad572d4ca6ee7019241f5e2cf7e4d999","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"DRAFT"}]},{"eval_id":"019e0083-0a96-77f4-a106-fb583482c798","probe":"How much did the General Land Office (GLO) increase?","golden":"$860 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$860 thousand"}]},{"eval_id":"019e0083-5461-7354-8851-9512e63b1c22","probe":"How much did the Texas Commission on Environmental Quality (TCEQ) increase?","golden":"$543 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$543 thousand"}]},{"eval_id":"019e0083-c942-7b97-83f8-c0423a20e2a4","probe":"How much did the Federal Emergency Management Agency (FEMA) decrease?","golden":"$420 thousand","png_sha":"a1493942ea92da912374a06e4de2e0cb0fb297b4b02d335f4c0f81f8ee5fd6bd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand decrease"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand decrease"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand decrease"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand decrease"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$420 thousand"}]},{"eval_id":"019e0084-65de-77d8-92f6-79df23bc1fad","probe":"What is the phone number for Pattillo, Brown & Hill, L.L.P.?","golden":"254.772.4901","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"254.772.4901"}]},{"eval_id":"019e0084-dffc-7ecf-b0c1-44b81836ebdd","probe":"What is the date of the year ended for the audit?","golden":"September 30, 2024","png_sha":"f706e29a3eff3e748675d0eecd62d012449c070cecd80bf87ca3e29ae98d9584","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"September 30, 2024"}]},{"eval_id":"019e00a1-03cf-7de0-9353-8ede1f29d21e","probe":"What time did the House meet?","golden":"10 a.m.","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"10 a.m."}]},{"eval_id":"019e00a2-8827-7350-ac1d-d1e691c7bc93","probe":"Which Congress's proceedings does this issue cover?","golden":"119th","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 119th Congress"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 119th Congress"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 119th Congress"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 119th Congress"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 119th Congress"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 119th Congress"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 119th Congress"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Proceedings and debates of the 119th Congress, first session"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 119th Congress"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 119th Congress"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress."},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 119th Congress"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The 119th Congress"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"119th Congress"}]},{"eval_id":"019e00a4-39cf-73f5-a08d-bdaf6f0e9555","probe":"Which state is Mrs. Trahan from?","golden":"Massachusetts","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Massachusetts"}]},{"eval_id":"019e00a4-9927-7270-b177-688639d2d84a","probe":"Which state is Mr. Thompson from?","golden":"Pennsylvania","png_sha":"f3224cb9b1b8ec637f41e04e7d61976df7cfb107ef883c8c7496a09f201de327","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pennsylvania"}]},{"eval_id":"019e00a5-86fd-7ef3-9421-534e8a66b6ef","probe":"How many 'yeas' were there in Roll No. 20?","golden":"214","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"214"}]},{"eval_id":"019e00a6-329c-73a0-9a01-cd95583196e9","probe":"How many 'nays' were there in Roll No. 20?","golden":"204","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"204"}]},{"eval_id":"019e00a7-701e-7774-bdaa-4a60fe45e545","probe":"What is the page number shown at the top left?","golden":"H276","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"H276"}]},{"eval_id":"019e00a7-fb7c-797d-8520-954d5503a748","probe":"What is the Roll number for the vote shown on this page?","golden":"20","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"20"}]},{"eval_id":"019e00ad-d3ed-7216-853a-30e02dbd1131","probe":"Who is the first name listed alphabetically in the NAYS column?","golden":"Adams","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adam Schiff"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adam Schiff"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adam Schiff"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adam Schiff"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adams"}]},{"eval_id":"019e00b0-cecb-7e7c-8149-7640c1dad861","probe":"Which member changed their vote from \"nay\" to \"yea\"?","golden":"Mr. Palmer","png_sha":"455d7b695a4f93feffc993b53345b1d8bdc7b37cc52920efcac2e0f6b4aa3fec","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Mr. PALMER"}]},{"eval_id":"019e00b3-c235-73fb-ba21-0118c8eadbf3","probe":"What is the page number shown in the top-left corner?","golden":"S250","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S250"}]},{"eval_id":"019e00b4-9c27-73de-8223-11187c914c6f","probe":"What is the date shown at the top-right of the page?","golden":"January 20, 2025","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"January 20, 2025"}]},{"eval_id":"019e00bc-df61-7504-ab8f-56af050077d7","probe":"Who is being considered for Secretary of State on Executive Calendar No. 2?","golden":"Marco Rubio","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO of Florida"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida is being considered for Secretary of State on Executive Calendar No. 2"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO of Florida"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO of Florida"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio of Florida."},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO of Florida"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Marco Rubio"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"MARCO RUBIO of Florida"}]},{"eval_id":"019e00bf-a471-719a-84c8-972702dced95","probe":"What dollar amount is mentioned as the threshold for financial harm to a State or its residents?","golden":"$100","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"$100"}]},{"eval_id":"019e00c1-d9d4-7426-9471-e13471bf2c6f","probe":"How many nays were there on the vote on Amendment No. 8?","golden":"24","png_sha":"2b581224f3c2fe7d4fe85fb8cadd0f11b29acdc8a51ec5b9701cdc010c2af4a3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"24"}]},{"eval_id":"019e00c6-5871-7da2-a93b-3aefb5c66f16","probe":"What is the page number shown at the top left?","golden":"S2714","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S2714"}]},{"eval_id":"019e00c9-c213-7e12-b66f-043b2559c706","probe":"Who is being nominated to be Lieutenant Commander in the Coast Guard?","golden":"John O. Mansolillo","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"John O. Mansolillo"}]},{"eval_id":"019e00ce-9d49-7844-bd6c-346e75c0b284","probe":"What is the bill number for the bill to direct the Secretary of the Treasury to stop minting the penny?","golden":"S. 1525","png_sha":"a9774663903fedd9b7a3e62e6871205ee706ced75b034179f8f2c400ca0f7cc9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525\nEVIDENCE \"S. 1525. A bill to direct the Secretary of the Treasury to stop minting the penny...\""},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S.1525"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"S. 1525"}]},{"eval_id":"019e051c-6f18-78b3-a1d7-9d8a0a2b9618","probe":"How many senators voted yea on the Driscoll nomination?","golden":"66","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66"}]},{"eval_id":"019e0520-d920-72fd-9146-7ff4401c225d","probe":"Did Senator Booker vote yea or nay on the Driscoll nomination?","golden":"nay","png_sha":"49052237fbdff75ab26fb835a0c50e112c08ecb8a7a5eab1d861767fdcf5efb5","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"nay"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nay"}]},{"eval_id":"019e0523-07a2-7eed-a522-32a019057e4b","probe":"Under what clause and rule were sponsors added to public bills?","golden":"clause 7 of rule XII","png_sha":"16dcdd10b145aee7117557debfdafca1da3f4ed251de5168731468a1944a374e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Under clause 7 of rule XII"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Clause 7 of rule XII"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Under clause 7 of rule XII"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"clause 7 of rule XII"}]},{"eval_id":"019e053e-4d48-7017-b80c-96993dddb76d","probe":"How many patients were in the SOC alone group?","golden":"4,321","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321\nEVIDENCE \"SOC alone (n = 4,321)\""},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"}]},{"eval_id":"019e053f-1f3f-7cd4-9bdf-bb8319b59261","probe":"What is the table number and title?","golden":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 5a. Systemic Corticosteroids: Selected Clinical Trial Data"}]},{"eval_id":"019e0540-facb-7b6a-8fd8-3f509341da68","probe":"What was the mean age of participants in the RECOVERY trial?","golden":"66 years","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"66 years"}]},{"eval_id":"019e0541-5acc-73a2-a0f0-4a8a3fd3f3d7","probe":"When was this table last updated?","golden":"February 29, 2024","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"February 29, 2024"}]},{"eval_id":"019e0542-7270-77f1-aa19-55066dadd841","probe":"How many patients were in the SOC alone group?","golden":"4,321","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"4,321"}]},{"eval_id":"019e0543-15cb-749c-890f-dc25b546fa1f","probe":"What percentage of participants had laboratory-confirmed SARS-CoV-2 infection?","golden":"89%","png_sha":"6b2d2c8de5b0666b56fb55e866bd044fa451ca7e8a21c88e415eea9e942c6b38","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"89%"}]},{"eval_id":"019e0547-98af-7c91-aa30-6a7096eca524","probe":"What is the table number and title shown at the top of the page?","golden":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Table 2c. Therapeutic Management of Hospitalized Adults With COVID-19"}]},{"eval_id":"019e0547-eecc-7d07-95de-24c48450b6a5","probe":"On what date was this document downloaded according to the bottom of the page?","golden":"3/1/2024","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"}]},{"eval_id":"019e0549-117f-704c-b2ed-3771bcbf57de","probe":"What is the URL shown at the bottom of the page where this document was downloaded from?","golden":"https://www.covid19treatmentguidelines.nih.gov/","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"https://www.covid19treatmentguidelines.nih.gov/"}]},{"eval_id":"019e054a-48f1-7ae1-8c9a-f98de9d0fa5b","probe":"What is the recommendation for patients hospitalized but not requiring supplemental oxygen who are at high risk of progressing to severe COVID-19?","golden":"Remdesivir","png_sha":"d21585694856000ae5323ff5370b3c2d17db6b628a726d01e862dc564fcfc76e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb)"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb)"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb)"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb)"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb)"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb)"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb)"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb)"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients."},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb)"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb)"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb)"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Remdesivir (BIIb) for patients who are immunocompromised; (BIII) for other high-risk patients"}]},{"eval_id":"019e0550-1990-7266-9919-560f19c4cee5","probe":"In the CATCO trial, what percentage of patients received corticosteroids?","golden":"87%","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"87%"}]},{"eval_id":"019e0550-c523-7e3c-a7bb-5e58b208e5dc","probe":"In the CATCO trial, what percentage of patients were on conventional oxygen?","golden":"54%","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"54%"}]},{"eval_id":"019e0553-86d1-71ca-b900-5bbaabb7ca45","probe":"How many randomized controlled trials were included in the pooled analysis of individual data mentioned with ACTT-1?","golden":"9","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9"}]},{"eval_id":"019e0555-7910-7ed7-a44b-456f65b6a4b0","probe":"Approximately what fraction of patients in the Solidarity trial received corticosteroids?","golden":"two-thirds","png_sha":"be2b6b4951fbe48f36be7f0811c5333b12c7c080a8ed5edb0a9755018439b288","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Two-thirds"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"two-thirds"}]},{"eval_id":"019e055a-07af-77a5-89c9-42e3d3fa137d","probe":"What is the maximum daily dose of low-dose aspirin?","golden":"81 mg","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"** 81 mg\n**"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"81 mg"}]},{"eval_id":"019e055f-c91a-7e0f-9401-67c36bb17b91","probe":"According to the Key, what does CAA stand for?","golden":"coronary artery aneurysm","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Coronary artery aneurysm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"coronary artery aneurysm"}]},{"eval_id":"019e0561-73ca-7c46-9bf0-5c643e61cde3","probe":"What does IBW stand for according to the Key?","golden":"ideal body weight","png_sha":"10759cbd902432a54cb91feb743aa390e88703b990220ee1ff87917a6ee2833c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal Body Weight"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal Body Weight"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal Body Weight"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal Body Weight"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal Body Weight"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal Body Weight"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal Body Weight"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal Body Weight"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal Body Weight"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal body weight"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ideal Body Weight"}]},{"eval_id":"019e05a7-e018-7ce5-b33f-396e12ec5cd7","probe":"What is the risk level for moderately or severely immunocompromised patients regardless of vaccination status?","golden":"High","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"High"}]},{"eval_id":"019e05a9-4840-7d85-a06e-f789e706a095","probe":"What is the risk level for patients with mild asthma, overweight, or well-controlled diabetes?","golden":"Low","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Low"}]},{"eval_id":"019e05ab-8ba2-7ab7-87ce-36b3ba6a8e47","probe":"What is the risk level shown for patients with sickle cell disease or chronic kidney disease?","golden":"Intermediate","png_sha":"ddf0c2e393620835bcb054dfb3079fd1fdd8489046a12060e3aeca49493e6085","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intermediate"}]},{"eval_id":"019e05b0-6eee-79fe-9c1a-85e69f5d1b78","probe":"What is the page number?","golden":"174","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"174"}]},{"eval_id":"019e05b0-9f88-7493-8093-1faf321a65c1","probe":"What is the date the document was downloaded?","golden":"3/1/2024","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"3/1/2024"}]},{"eval_id":"019e05b0-d9cd-707e-a8fc-05816b33e002","probe":"What is the title of this section shown in the orange header?","golden":"Summary Recommendations, continued","png_sha":"58854b07e54ad827bb639b5f859d448c8dac20d437a6fef21eab0c4c4406711f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Summary Recommendations, continued"}]},{"eval_id":"019e05b1-edb1-71fd-a8f1-178c8ce2372a","probe":"How many hours per day of prone ventilation does the Panel recommend?","golden":"12 to 16 hours","png_sha":"f2687af1be946044a236b7f11f8cf6f728ef1c4e9e442378d2a6ad846b6a54e4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours per day"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"12 to 16 hours"}]},{"eval_id":"019e05ba-b872-7e8f-9ab0-ebf540496835","probe":"How many people were in the placebo group?","golden":"761","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"761"}]},{"eval_id":"019e05bd-b79d-79ce-83a2-61bee82f41bd","probe":"What was the mean age of participants?","golden":"58 years","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"58 years"}]},{"eval_id":"019e05bd-fce1-7c37-9985-6a2be13c70b5","probe":"What percentage of participants received corticosteroids?","golden":"79%","png_sha":"f8a4cfcc647eabea621d40638837aa18dd6e2a6a2ce3e580bc8258f2e72d11cd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"79%"}]},{"eval_id":"019e05bf-8d4e-7984-b130-f857ef177151","probe":"What is Pablo Tebas's financial disclosure relationship with Shionogi?","golden":"Consultant","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"}]},{"eval_id":"019e05c0-2875-7f53-8cd2-1afd5c604eef","probe":"What is Andrew T. Pavia's relationship with Haleon?","golden":"Honoraria","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Honoraria"}]},{"eval_id":"019e05c1-9d7a-7ef6-8d4a-75d9a4d8bc53","probe":"What is Grant Schulert's financial disclosure relationship with Boehringer Ingelheim?","golden":"Consultant","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Consultant"}]},{"eval_id":"019e05c2-9694-7119-b6c6-e2863ab93d51","probe":"What company is Phyllis Tien disclosed as receiving research support from?","golden":"Merck","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Merck"}]},{"eval_id":"019e05c3-4ee4-7de9-abf1-e04c45c9b57f","probe":"What is Susan Swindells's financial disclosure relationship with GSK/ViiV Healthcare?","golden":"Research support","png_sha":"cc11007d170891647819808f6e914314420dde8c195ee2eea2df4de15e1b30f3","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research Support"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Research support"}]},{"eval_id":"019e05e7-8068-7743-a656-13b1d4d4190b","probe":"How many chapter objectives are listed on this page?","golden":"5","png_sha":"4fb66d797829b4efe7d38ed6d367871d6664885f70ef83a42d3f0dfec31552e6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e05f2-f42c-7018-ab71-30b51adf12e2","probe":"What is the name of the region located between the right and left lumbar regions?","golden":"Umbilical region","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Umbilical region"}]},{"eval_id":"019e05f3-f4bd-74db-9544-35cd14788275","probe":"What is the name of the region directly above the umbilical region?","golden":"Epigastric region","png_sha":"71e61fe3fb202d40d9cf3da5eaf2775ecb508bc1cfda7c8e32d12ae24c7aba0b","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Epigastric region"}]},{"eval_id":"019e05f6-e2c6-7b53-b37c-1808bd28b0d4","probe":"What organ is shown as the example at the Organ level in the pyramid?","golden":"Bladder","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Bladder"}]},{"eval_id":"019e05f9-174d-779b-8451-840365bb3ab1","probe":"What type of muscle cell is shown at the Cellular level in the pyramid?","golden":"Smooth muscle cell","png_sha":"79f9a219359c3966dd4eec4ab0309aaa593a8a41829c5951e8d4845236154f5e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Smooth muscle cell"}]},{"eval_id":"019e05fa-5cd7-7bf5-ad75-0aa2f060da1e","probe":"What is the name of the plane shown at the bottom of the figure, near the body's feet?","golden":"Oblique plane","png_sha":"d0de1bb560e9b722942304e532a14882201f7692dbe44333b38e37a146f08834","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oblique plane"}]},{"eval_id":"019e0a71-d77a-7463-8c88-e70ccbeb93a7","probe":"How many electrons are shown in the cloud of negative charge?","golden":"2","png_sha":"b2e31f2db4376ca05a0ed9dbaca4c903d11f9b30380161d0923d8dcfa7c69d18","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"2"}]},{"eval_id":"019e0a78-60c3-7ff1-a58d-36cf79d83532","probe":"What is the pH of blood?","golden":"7.4","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"7.4"}]},{"eval_id":"019e0a78-c1e6-7be1-b2ed-7370055ce7a4","probe":"What is the pH of baking soda?","golden":"9.5","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"9.5"}]},{"eval_id":"019e0a79-38e3-7203-9d9c-b65c2c843999","probe":"What is the pH of black coffee?","golden":"5","png_sha":"34aaf1cfe541aba0a675a57014bc347d10fa24d5abece7aa2755251c3f3733f4","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"pH=5"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"5"}]},{"eval_id":"019e0a7f-36c1-76f1-9b7d-a75d3f8b57bc","probe":"What are the regions of the enzyme called where substrates bind?","golden":"Active sites","png_sha":"56f42b1466f0ba4fd23da4bdafef8224d214d10ff10aa671d80ddc4389ea94dd","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"active sites"}]},{"eval_id":"019e0a7f-f372-7caa-bdd1-9371e7bc0c6a","probe":"How many chromosomes does the page say are inside the nucleus of each cell?","golden":"46","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46 chromosomes"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"46"}]},{"eval_id":"019e0a80-2d48-78ae-9837-df877d92d50a","probe":"Approximately how many genes do humans have in their DNA according to this page?","golden":"22,000","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22000"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"22,000"}]},{"eval_id":"019e0a80-c197-7fce-a219-ddb90e59c15f","probe":"What color represents Guanine in the diagram?","golden":"Blue","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"}]},{"eval_id":"019e0a81-1a13-7011-bf33-0b2b8c97db32","probe":"What color represents Adenine in the diagram?","golden":"Red","png_sha":"62a1f63d5cf15ecf64dd41a150aaf2d8660df4bb65e65ed326de484753d69d5f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red"}]},{"eval_id":"019e0a83-ca15-7698-adf8-be9e8fecc270","probe":"What is labeled as the area inside the cell in the large membrane illustration?","golden":"Intracellular","png_sha":"a2c418cbcdc6704d925ad4ffdd78dee38a58fc1ea68774d0094b65c486a66bf8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Intracellular"}]},{"eval_id":"019e0a91-1c2e-7311-b881-fc5c00ce52f9","probe":"What does the arrow at the bottom of the diagram represent?","golden":"Time","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"The passage of time"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"}]},{"eval_id":"019e0a91-e6fb-79fb-b85f-ccfa87b7f449","probe":"What is labeled above the lipid bilayer in the center of the diagram?","golden":"Extracellular fluid","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Extracellular fluid"}]},{"eval_id":"019e0a92-7404-7aab-b271-b5cbb06491b3","probe":"What is labeled below the lipid bilayer in the center of the diagram?","golden":"Cytoplasm","png_sha":"362e47b72d907b12233e18233536942542f3f361f31ccf5e10f5ba8f775b492a","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytoplasm"}]},{"eval_id":"019e0a94-7773-7d3d-b4db-4925da2a4c81","probe":"What are the three labels above the cell images in Figure 3.1.6?","golden":"Hypertonic, Isotonic, Hypotonic","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic."},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hypertonic, Isotonic, Hypotonic."}]},{"eval_id":"019e0a94-dfda-768c-897f-34618204bf19","probe":"What is labeled between the two beakers in Figure 3.1.5?","golden":"Semipermeable membrane","png_sha":"94f63ffffa4b4e952770199fc006a806aab9fd5cbfed35d233b1fad7081a1239","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Semipermeable membrane"}]},{"eval_id":"019e0aa6-cdb4-70a0-951f-040144680d97","probe":"What is labeled in purple at the center of the diagram?","golden":"Crystalline core","png_sha":"29f66040d5b404ad4868b569f57abcbd771a080fa8fcc185a3187093b4d3defb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Crystalline core"}]},{"eval_id":"019e0ab1-a72f-70b0-9619-a8e2a81fee46","probe":"What are the four nitrogenous bases listed in the legend?","golden":"Adenine, Thymine, Guanine, Cytosine","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Adenine, Thymine, Guanine, Cytosine"}]},{"eval_id":"019e0ab3-3b2c-7cf7-9e5a-87076b99eb2f","probe":"What color is used to represent Guanine in the legend?","golden":"Blue","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"blue"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blue"}]},{"eval_id":"019e0ab4-5e27-7fa0-bdb3-55833bf40f16","probe":"What type of bonds connect the two DNA strands together according to the diagram?","golden":"Hydrogen bonds","png_sha":"bf790a65d5b6266294acfabe6938f770f5ed6a6d118abaf072c7fa8912bb33b8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hydrogen bonds"}]},{"eval_id":"019e0ac8-36ba-7365-9435-ec92bf202c05","probe":"According to figure 3.5.3, what is the first phase of mitosis?","golden":"Prophase","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Prophase"}]},{"eval_id":"019e0ac9-ab1a-7551-88fe-ba669d0ab987","probe":"What is the last stage shown in the cell division diagram (after telophase)?","golden":"Cytokinesis","png_sha":"4e57e305cdcd900e0059f99a58147b0e2d9346596938d8b24b357aa7c093e5f2","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Cytokinesis"}]},{"eval_id":"019e0ad3-52d5-7f4c-8d3d-591d2476cefd","probe":"What is at the very top of the stem cell differentiation diagram?","golden":"Totipotent embryonic stem cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"}]},{"eval_id":"019e0adb-d424-739a-88c3-a9c6837b69aa","probe":"What type of stem cell is at the top of the diagram?","golden":"Totipotent embryonic stem cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Totipotent embryonic stem cell"}]},{"eval_id":"019e0ae7-f32b-7670-af77-ced5432c5f69","probe":"What specialized cell type is shown between 'Heart muscle' and 'Skin' in the bottom row?","golden":"Red blood cell","png_sha":"7e874ca1610b8072b941eb9b327a798c6ab477203076f2a481912c8a1fdf804e","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Red blood cell"}]},{"eval_id":"019e0b0b-0842-7562-aaee-a34590209d11","probe":"What is the figure title for Figure 4.6.2?","golden":"Development of Cancer","png_sha":"c97dbfb9dac36762398856cdab61d5779eae44284b94b744c8e56704bbf954e8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Development of Cancer"}]},{"eval_id":"019e0b35-2b57-7c4e-9af5-fa094b59bb2c","probe":"What cell type is shown in the bottom-right image of the diagram?","golden":"Pancreatic cell","png_sha":"7b24760285552c0a3e2beb4a713373cf7079657b1996b630c4cab49bb81d2a0c","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Pancreatic cell"}]},{"eval_id":"019e0eb0-b4d4-72a3-99bd-8214864274dd","probe":"Which long bone is shown as the example in the diagram?","golden":"Femur","png_sha":"649d7b93ee3bd97ec82fa0d6dc7eb1ef1d3a531661aaf8e5a64a2e776e7befdf","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Femur"}]},{"eval_id":"019e0eb5-35af-7967-8d48-00aa0aa1a645","probe":"According to table 11.4, what is the origin of the superior oblique?","golden":"Sphenoid bone","png_sha":"e52a483f3e3402fc6874a991f546b566e2a6a0e32ba17df2ef455c46bc8e0793","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Sphenoid bone"}]},{"eval_id":"019e0eb9-5156-79fe-85f7-13b631e40c4d","probe":"What is the bone labeled between the Tibia and the Tarsals on the lower leg?","golden":"Fibula","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Fibula"}]},{"eval_id":"019e0eb9-c545-743f-b1c1-6053776f3ffb","probe":"What bone is labeled directly below the Humerus on the arm?","golden":"Ulna","png_sha":"951b5c3411ad5d47fd979d47afebdcd59fa71347d67fafe2f53ec5021aac69c9","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ulna"}]},{"eval_id":"019e0ebd-9465-739b-8454-3efaee4d4310","probe":"What is the label directly below 'Rotator brevis' in the Deep spinal muscles diagram?","golden":"Rotator longus","png_sha":"8267a338f131676cd4f156eb0c4a18c6d48352ad7a386fd12707e7503673af3f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Rotator longus"}]},{"eval_id":"019e0ebf-4889-76bf-9d21-fdeaa9903ac1","probe":"On the left hand side of the left lateral view, what muscle is labeled directly above the Anterior scalene?","golden":"Medial scalene","png_sha":"8267a338f131676cd4f156eb0c4a18c6d48352ad7a386fd12707e7503673af3f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Medial scalene"}]},{"eval_id":"019e0eca-119a-763f-ac56-f38e33c22003","probe":"What four carpal bones are labeled in the figure 8.2.5?","golden":"Hamate, Trapezoid, Trapezium, Capitate","png_sha":"306e13b6e12dfea3dcc83ac66671b7f4f26e03a8658a38703694470c4b84acff","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate Trapezoid Trapezium Capitate"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate Trapezoid Trapezium Capitate"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Hamate, Trapezoid, Trapezium, Capitate"}]},{"eval_id":"019e0ecd-0967-77f3-a1b2-140685a06b07","probe":"What structure is labeled at the very top of the cell?","golden":"Microvilli","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Microvilli"}]},{"eval_id":"019e0ecd-62a5-7179-841c-8e4ba5c98a0a","probe":"What structure is labeled at the very bottom of the cell?","golden":"Nucleus","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Nucleus"}]},{"eval_id":"019e0ece-41ab-74ba-b577-6e0aff6ee57c","probe":"What labeled structure appears between the Rough ER and the Nucleus?","golden":"Golgi apparatus","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Golgi apparatus"}]},{"eval_id":"019e0ece-aeb7-7000-b806-b1e7d144e6f6","probe":"What color is used to depict the Golgi apparatus in this figure?","golden":"orange","png_sha":"4964e97b272464d4979ccf46b57ef0b96770e53704b77af012ea3214ad0c7482","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"orange"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Orange"}]},{"eval_id":"019e0ed1-c40b-7515-aa9e-86ffff7a7b0a","probe":"In figure (a), labeled \"Loosely held,\" what object is being held?","golden":"a pencil","png_sha":"294a4958d5ff0d4328b9ea9e75f13bb4f7ef1d09ee59316db09945f970fa281f","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"a pencil"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"A pencil"}]},{"eval_id":"019e0ed6-4075-7e2a-8d36-a54c01ef1f0a","probe":"According to the labels in the figure, which Roman numeral is assigned to the Olfactory nerve?","golden":"I","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"I"}]},{"eval_id":"019e0ed7-29c1-7353-a0d0-78dc86f5bf0d","probe":"Which cranial nerve is labeled with the Roman numeral X?","golden":"Vagus nerve","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Vagus nerve"}]},{"eval_id":"019e0ed7-a580-70c5-9af2-82e1e6d3b27c","probe":"Which cranial nerve is labeled directly above the Trochlear nerve on the left side of the figure?","golden":"Oculomotor nerve","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Oculomotor nerve"}]},{"eval_id":"019e0ed8-e384-740f-8339-b731e7477bd0","probe":"Which Roman numeral is assigned to the Trigeminal nerve?","golden":"V","png_sha":"1d4c2f7431ef8193ebaad80b519247e6776196dad85799391e2f8024674f2686","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"V"}]},{"eval_id":"019e0ee0-04e8-7f4f-a3d3-f732f8ce4367","probe":"What does the x-axis represent?","golden":"Time","png_sha":"ac44511d23ca4ddd39f6ebec611c5456b158b414fc08c7f1fccde66ba0ebc3c8","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Time"}]},{"eval_id":"019e0ee4-1b7c-773f-963c-fc9c8846cdc2","probe":"In the rightmost (third) illustration of Figure 14.1.1, what label appears at the far right?","golden":"Ectoderm","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Ectoderm"}]},{"eval_id":"019e0ee5-7413-77ac-928e-9349a0add2e3","probe":"In the far-left illustration of Figure 14.1.1, what word is labeled at the end of the curved arrow?","golden":"Convergence","png_sha":"4b57e7b25ad0c75513e48c67783774c414850252fd371f5578f19334cca2f0c6","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence."},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Convergence"}]},{"eval_id":"019e0ee7-d44b-7f7f-9dde-44db50c5a6d7","probe":"In panel (a), what label is shown at the top-left of the panel?","golden":"Resting muscle","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Resting muscle"}]},{"eval_id":"019e0ee8-0c80-7766-bb63-e01a6477af62","probe":"In panel (a), what label is shown at the top-right of the panel?","golden":"Active muscle","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Active muscle"}]},{"eval_id":"019e0ee8-b795-7df0-985e-b6a23bc84e11","probe":"In panel (b), what process is shown at the top-right when oxygen is present?","golden":"Aerobic respiration","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Aerobic respiration"}]},{"eval_id":"019e0ee9-027b-7c34-9c19-e3a9f92ddc36","probe":"In panel (b), what is produced when there is no oxygen?","golden":"Lactic acid","png_sha":"a77f0836ed7597291b1767b8f17ff88e52a050597e5b5798948f335a965206cb","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid to blood"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"lactic acid"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Lactic acid"}]},{"eval_id":"019e0eee-1192-75e7-bc00-9eba77492379","probe":"In Figure 17.5.2, what does step 1 say?","golden":"Blood calcium concentration drops","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium concentration drops"}]},{"eval_id":"019e0eee-6b0f-7623-9bf9-f65dcda769bd","probe":"In Figure 17.5.2, what does step 4 say?","golden":"Blood calcium levels increase","png_sha":"0a91991c0b238bf025bd66e1e8440ad43789a0ace2ad5ea409b8edfb9c5d1d47","worst":2,"best":2,"cells":[{"run_index":0,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":1,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":2,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":3,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":4,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":5,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":6,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":7,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":8,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":9,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":10,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":11,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":12,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":13,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":14,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":15,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":16,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":17,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":18,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":19,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":20,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":21,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":22,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":23,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":24,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":25,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":26,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":27,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":28,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"},{"run_index":29,"verdict":2,"source":"auto","note":"normalized substring match","answer":"Blood calcium levels increase"}]}]}]}